Soccer predictions: actual data vs predicted data

Slate 20261024 · 8 match(es)

How to read this report. Each match shows the model's headline prediction, the stage-by-stage lambda (goal-rate) build, both teams' standing/form inputs, and every starter's projected line next to their real season baseline. A moderate / large deviation badge flags a projection that strays far from the player's season form — a quick way to spot when the inputs look right but a projection does not. When the real result is known an actual-vs-predicted banner appears.

All matches overview

Match	Score	Winner	H / D / A	O2.5	BTTS	Conf	λ H/A	Actual	Result
Atlético Madrid vs Deportivo LaLiga	2-0	Atlético Madrid	82.9% / 11.5% / 5.6%	69.0%	45.4%	0.84	2.90 / 0.66	-	pending
Rayo Vallecano vs Elche LaLiga	1-1	Draw	40.4% / 27.8% / 31.9%	43.0%	48.7%	0.7	1.29 / 1.11	-	pending
Racing Club vs Espanyol LaLiga	1-1	Draw	33.8% / 25.6% / 40.6%	52.4%	56.2%	0.7	1.31 / 1.46	-	pending
Arsenal vs Everton Premier League	1-0	Arsenal	56.9% / 22.7% / 20.4%	54.7%	53.9%	0.76	1.85 / 1.02	-	pending
Coventry vs Fulham Premier League	1-1	Draw	34.1% / 27.2% / 38.7%	45.6%	50.9%	0.7	1.20 / 1.30	-	pending
Aston Villa vs Man City Premier League	0-2	Man City	10.4% / 15.3% / 74.3%	68.1%	54.7%	0.8	0.89 / 2.62	-	pending
Chelsea vs Tottenham Premier League	1-0	Chelsea	54.8% / 23.3% / 21.9%	53.8%	54.0%	0.75	1.79 / 1.04	-	pending
Valencia vs Villarreal LaLiga	0-1	Villarreal	23.2% / 26.9% / 49.9%	41.7%	45.5%	0.74	0.90 / 1.45	-	pending

Match detail

Atlético Madrid vs Deportivo

LaLiga · 20261024 · 4-2-3-1 vs 4-2-3-1

Predicted 2-0Winner: Atlético MadridWinning H 2-0 (12.0%)Winning A 0-1 (1.8%)Confidence 0.84λ home/away 2.90 / 0.66Most-likely P 12.0%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Atlético Madrid vs Deportivo. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 2.657, Away 0.808). Final calibrated Poisson lambdas: Home 2.903, Away 0.655 (most likely score 2-0).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 2.66 / 0.81 Final λ (H/A) 2.90 / 0.66

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Atlético Madrid	Deportivo
League position	2.00	9.00
Points per game	2.01	1.28
Attack index	1.22	0.93
Defense (concede) index	0.90	0.86
Form multiplier	1.04	0.96
Standing λ multiplier	1.05	0.91

Lambda decomposition (how the goal rates were built)

Stage	Atlético Madrid λ	Deportivo λ
Pre-mismatch	2.790	0.768
Pre-calibration (Micro-duels)	2.657	0.808
Final λ	2.903	0.655

competition calibration scale 1.0competition observed total goals 0.0quality gap applied Truemismatch score pressure applied Truecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
2-0	12.0%
3-0	11.6%
4-0	8.4%
1-0	8.3%
2-1	7.9%

Home win	82.9%
Draw	11.5%
Away win	5.6%
Over 2.5	69.0%
BTTS yes	45.4%

Pregame fair line — favorite Atlético Madrid (82.9%), fair total 3.56, fair spread 2.25

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Atlético Madrid — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Marc Pubill D 80 0 0.09 0.04 142% 1 0.4 6.8 50.2 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0151, quality 0.817)	`market_value_eur=48000000` `quality_factor=0.8168` `boost_factor=1.0151` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0119)	`blend_weight=0.0119` `history_matches=26` `season_overlap_discount=1.0` `per90_to_match_factor=0.891` `prior_reliability=0.1133` `competition=La Liga`	interceptionWon: 0.8317 -> 0.8218 totalShots: 0.5277 -> 0.5337
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yeremay Hernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.0547 -> 0.0916 expected_assists: 0.0207 -> 0.0347
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 87.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0875` `goal_rate=0.1339` `scorer_weight=0.1145`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0341` `assist_rate=0.0083` `provider_weight=0.0286`	-

Marcos Llorente D 83 0 0.09 0.04 147% 1 0.6 7.0 60.0 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0047, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0047` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0076)	`blend_weight=0.0076` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.921` `prior_reliability=0.1` `competition=La Liga`	fouls: 0.7435 -> 0.7657 totalCross: 1.7694 -> 1.756 interceptionWon: 1.0512 -> 1.0618 wasFouled: 0.239 -> 0.2465
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yeremay Hernández', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.0567 -> 0.0949 expected_assists: 0.0898 -> 0.1504
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 85.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0905` `goal_rate=0.0` `scorer_weight=0.0759`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1396` `assist_rate=0.108` `provider_weight=0.17`	-

Jan Oblak G 90 0 0.00 - n/a 0.0 7.0 57.7 27 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0029, quality 0.590)	`market_value_eur=16000000` `quality_factor=0.59` `boost_factor=1.0029` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0148)	`blend_weight=0.0148` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Bil Nsongo, Yeremay Hernández', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.8083}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	shots_faced: 7.7 -> 6.2 expected_saves: 1.89 -> 1.51 high_pressure_saves: 0.65 -> 0.52
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 88.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=3.0444`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=1.8319`	-

Dávid Hancko D 88 0 0.11 0.05 124% 1 0.7 7.1 54.4 27 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0086, quality 0.758)	`market_value_eur=36000000` `quality_factor=0.7581` `boost_factor=1.0086` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0148)	`blend_weight=0.0148` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9769` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.0738 -> 1.0868 wasFouled: 0.2145 -> 0.2258 wonTackle: 0.7181 -> 0.7267
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yeremay Hernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.0664 -> 0.1112 expected_assists: 0.0501 -> 0.0839
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 83.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1052` `goal_rate=0.0` `scorer_weight=0.089`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0805` `assist_rate=0.1745` `provider_weight=0.1049`	-

Alejandro Grimaldo M 88 0 0.31 0.20 58% 2 1.3 7.1 52.1 19 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0139, quality 0.625)	`market_value_eur=19400000` `quality_factor=0.6251` `boost_factor=1.0139` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'José María Giménez', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.479, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.999, 'skill_edge': 0.0554, 'height_edge': -0.056, 'attacker_skill': 0.6251, 'defender_skill': 0.5021, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'José María Giménez', 'market_value': 5800000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.5021}], 'xg_override': 0.1848}	aerialWon: 0.4381 -> 0.8
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.1848 -> 0.3094 expected_assists: 0.1409 -> 0.2359
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 89.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2661` `goal_rate=0.1541` `scorer_weight=0.269`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.2101` `assist_rate=0.1344` `provider_weight=0.2279`	-

Morten Hjulmand M 84 0 0.10 0.03 292% 1 0.5 7.0 50.6 11 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0360, quality 0.817)	`market_value_eur=48000000` `quality_factor=0.8168` `boost_factor=1.036` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0350)	`blend_weight=0.035` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.9328` `prior_reliability=0.14` `competition=La Liga`	interceptionWon: 3.2197 -> 3.1536 fouls: 0.5548 -> 0.582 wonTackle: 1.0476 -> 1.0731 totalShots: 0.8561 -> 0.8418 onTargetScoringAttempt: 0.2078 -> 0.2005
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Diego Villares', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.599, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.263, 'skill_edge': 0.1829, 'height_edge': -0.004, 'attacker_skill': 0.8439, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Diego Villares', 'market_value': 1000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.061}	aerialWon: 1.5172 -> 1.2 totalShots: 0.8487 -> 1.0719 shotOffTarget: 0.6482 -> 0.8187 onTargetScoringAttempt: 0.2005 -> 0.2532 goals: 0.0593 -> 0.0749 expectedGoals: 0.0483 -> 0.061
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.061 -> 0.1021 expected_assists: 0.0531 -> 0.0889
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 83.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0971` `goal_rate=0.0749` `scorer_weight=0.1149`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0851` `assist_rate=0.0669` `provider_weight=0.1008`	-

Pablo Barrios M 74 0 0.13 0.03 296% 1 0.7 7.2 60.8 14 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0165, quality 0.879)	`market_value_eur=77000000` `quality_factor=0.8792` `boost_factor=1.0165` `reference_quality=0.505` `history_matches=29` `history_shrink=0.1471`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0147)	`blend_weight=0.0147` `history_matches=29` `season_overlap_discount=1.0` `per90_to_match_factor=0.818` `prior_reliability=0.1533` `competition=La Liga`	totalCross: 1.3818 -> 1.3668 wasFouled: 0.7955 -> 0.8099 totalShots: 0.9186 -> 0.9104 interceptionWon: 1.5158 -> 1.5092
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Diego Villares', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.603, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2695, 'skill_edge': 0.2034, 'height_edge': -0.02, 'attacker_skill': 0.8893, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Diego Villares', 'market_value': 1000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0753}	aerialWon: 0.754 -> 1.1 totalShots: 0.9203 -> 1.1683 shotOffTarget: 0.6781 -> 0.8608 onTargetScoringAttempt: 0.2422 -> 0.3075 expectedGoalsOnTarget: 0.0921 -> 0.1169 goals: 0.06 -> 0.0762 expectedGoals: 0.0593 -> 0.0753 bigChanceMissed: 0.0207 -> 0.0263
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.0753 -> 0.1261 expected_assists: 0.1306 -> 0.2187
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 83.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1185` `goal_rate=0.0762` `scorer_weight=0.127`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1964` `assist_rate=0.1249` `provider_weight=0.2118`	-

Julián Alvarez F 73 1 0.49 0.12 319% 3 1.4 7.0 52.0 21 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0150, quality 0.895)	`market_value_eur=107000000` `quality_factor=0.8953` `boost_factor=1.015` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0017)	`blend_weight=0.0017` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.8101` `prior_reliability=0.02` `competition=La Liga`	totalCross: 3.1189 -> 3.1137
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Lucas Noubi, Ximo Navarro', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.363, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.2394, 'skill_edge': 0.2029, 'height_edge': -0.04, 'attacker_skill': 0.8953, 'defender_skill': 0.4445, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Lucas Noubi', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}, {'player': 'Ximo Navarro', 'market_value': 95000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.295}	totalShots: 2.2917 -> 2.8403 shotOffTarget: 1.446 -> 1.7922 onTargetScoringAttempt: 0.8433 -> 1.0452 goals: 0.2884 -> 0.3574 expectedGoals: 0.238 -> 0.295 expectedGoalsOnTarget: 0.1863 -> 0.2309 bigChanceMissed: 0.1519 -> 0.1883
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.295 -> 0.4939 expected_assists: 0.0986 -> 0.1651
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 86.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3898` `goal_rate=0.3574` `scorer_weight=0.5832`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1522` `assist_rate=0.2564` `provider_weight=0.2064`	-

Ademola Lookman F 63 1 0.55 0.22 149% 3 1.5 6.8 57.2 28 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0170, quality 0.800)	`market_value_eur=44000000` `quality_factor=0.8002` `boost_factor=1.017` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0217)	`blend_weight=0.0217` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.7053` `prior_reliability=0.1733` `competition=La Liga`	wasFouled: 0.8095 -> 0.8213 totalShots: 2.0301 -> 2.0216 interceptionWon: 0.0142 -> 0.0198 totalCross: 0.7723 -> 0.7673
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Lucas Noubi, Ximo Navarro', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.336, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.2001, 'skill_edge': 0.1601, 'height_edge': -0.024, 'attacker_skill': 0.8002, 'defender_skill': 0.4445, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Lucas Noubi', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}, {'player': 'Ximo Navarro', 'market_value': 95000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.3273}	totalShots: 2.0321 -> 2.4388 shotOffTarget: 1.3062 -> 1.5676 onTargetScoringAttempt: 0.7259 -> 0.8712 bigChanceMissed: 0.4286 -> 0.5144 expectedGoals: 0.2727 -> 0.3273 goals: 0.2299 -> 0.2759 expectedGoalsOnTarget: 0.1327 -> 0.1593
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.3273 -> 0.5481 expected_assists: 0.1015 -> 0.1699
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 83.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.422` `goal_rate=0.2759` `scorer_weight=0.4734`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1563` `assist_rate=0.0` `provider_weight=0.1359`	-

Alex Baena F 73 0 0.37 0.09 319% 3 1.5 7.2 63.4 38 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0114, quality 0.817)	`market_value_eur=48000000` `quality_factor=0.8168` `boost_factor=1.0114` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0095)	`blend_weight=0.0095` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.8082` `prior_reliability=0.12` `competition=La Liga`	totalCross: 3.5951 -> 3.578 goals: 0.2277 -> 0.2383 interceptionWon: 1.3467 -> 1.3382 totalOffside: 0.1966 -> 0.2033 fouls: 1.1132 -> 1.1197 wasFouled: 1.235 -> 1.2403
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Lucas Noubi, Ximo Navarro', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.344, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.211, 'skill_edge': 0.1676, 'height_edge': -0.024, 'attacker_skill': 0.8168, 'defender_skill': 0.4445, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Lucas Noubi', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}, {'player': 'Ximo Navarro', 'market_value': 95000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.2206}	totalShots: 2.224 -> 2.6933 shotOffTarget: 1.3849 -> 1.6771 onTargetScoringAttempt: 0.8391 -> 1.0162 expectedGoalsOnTarget: 0.2492 -> 0.3018 goals: 0.2383 -> 0.2886 expectedGoals: 0.1822 -> 0.2206
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.2206 -> 0.3693 expected_assists: 0.2243 -> 0.3754
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 83.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.3088` `goal_rate=0.2886` `scorer_weight=0.4616`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.313` `assist_rate=0.0615` `provider_weight=0.3003`	-

Kang-in Lee F 74 0 0.33 0.14 134% 3 1.9 7.1 56.2 16 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0278, quality 0.764)	`market_value_eur=37000000` `quality_factor=0.7641` `boost_factor=1.0278` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Lucas Noubi, Ximo Navarro', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.316, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1703, 'skill_edge': 0.1439, 'height_edge': -0.028, 'attacker_skill': 0.7641, 'defender_skill': 0.4445, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Lucas Noubi', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}, {'player': 'Ximo Navarro', 'market_value': 95000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.1988}	totalShots: 2.1216 -> 2.4829 shotOffTarget: 1.4223 -> 1.6645 onTargetScoringAttempt: 0.6993 -> 0.8184 expectedGoalsOnTarget: 0.2602 -> 0.3045 goals: 0.189 -> 0.2212 bigChanceMissed: 0.1853 -> 0.2169 expectedGoals: 0.1699 -> 0.1988
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.90 (squad xG sum 1.7339, xG scale 1.6743, xA scale 1.6743, team xA 1.93 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=2.903` `squad_xg_sum=1.7339` `squad_xa_sum=1.1509` `team_expected_assists=1.9269` `team_xa_to_xg_ratio=0.6638`	expected_goals: 0.1988 -> 0.3328 expected_assists: 0.2044 -> 0.3422
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 80.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2831` `goal_rate=0.2212` `scorer_weight=0.3628`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.2898` `assist_rate=0.1007` `provider_weight=0.2738`	-

Team totals 2 2.90 21 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Juan Musso	G	4.4m	10.9%	Market-value substitute prior
Cristian Romero	D	15.0m	36.6%	Market-value substitute prior
Robin Le Normand	D	14.3m	23.2%	Market-value substitute prior
Giuliano Simeone	M	29.2m	46.5%	Market-value substitute prior
Rodrigo Mendoza	M	13.6m	45.2%	Market-value substitute prior
Jonathan David	F	26.4m	60.8%	Market-value substitute prior

Deportivo — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Bil Nsongo F 76 0 0.16 0.13 ok 2 1.6 6.9 52.4 13 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9958, quality 0.466)	`market_value_eur=5300000` `quality_factor=0.4659` `boost_factor=0.9958` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0248)	`blend_weight=0.0248` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8471` `prior_reliability=0.1067` `competition=La Liga`	wonTackle: 0.7266 -> 0.7611 fouls: 1.0715 -> 1.0974 totalCross: 0.3178 -> 0.3362 totalShots: 2.1371 -> 2.1228 wasFouled: 0.6833 -> 0.6926 goals: 0.2747 -> 0.2679 onTargetScoringAttempt: 0.7632 -> 0.7571
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Marc Pubill, Dávid Hancko', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7121, 'skill_edge': -0.1678, 'height_edge': -0.028, 'attacker_skill': 0.4659, 'defender_skill': 0.8388, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Marc Pubill', 'market_value': 48000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8608}, {'player': 'Dávid Hancko', 'market_value': 36000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8168}], 'xg_override': 0.1913}	totalShots: 2.131 -> 1.5175 shotOffTarget: 1.3739 -> 0.9784 onTargetScoringAttempt: 0.7571 -> 0.5391 expectedGoals: 0.2686 -> 0.1913 goals: 0.2679 -> 0.1908 expectedGoalsOnTarget: 0.1958 -> 0.1394 bigChanceMissed: 0.1746 -> 0.1243
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1913 -> 0.1647 expected_assists: 0.0421 -> 0.0311
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 69.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1519` `goal_rate=0.1908` `scorer_weight=0.1644`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0306` `assist_rate=0.0` `provider_weight=0.0249`	-

Yeremay Hernández F 78 0 0.09 0.16 42% 1 0.9 7.0 54.0 13 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0178, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0178` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0067)	`blend_weight=0.0067` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.8679` `prior_reliability=0.0267` `competition=La Liga`	wonTackle: 1.1939 -> 1.2149 totalCross: 2.4134 -> 2.3973 totalOffside: 0.0 -> 0.0145 totalShots: 1.5867 -> 1.5761 interceptionWon: 0.9585 -> 0.9521
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Marc Pubill, Dávid Hancko', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7932, 'skill_edge': -0.0807, 'height_edge': -0.06, 'attacker_skill': 0.6595, 'defender_skill': 0.8388, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Marc Pubill', 'market_value': 48000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8608}, {'player': 'Dávid Hancko', 'market_value': 36000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8168}], 'xg_override': 0.1084}	totalShots: 1.5834 -> 1.256 shotOffTarget: 1.1048 -> 0.8763 onTargetScoringAttempt: 0.4786 -> 0.3796 expectedGoalsOnTarget: 0.3098 -> 0.2457 goals: 0.1468 -> 0.1164 expectedGoals: 0.1366 -> 0.1084
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1084 -> 0.0934 expected_assists: 0.1334 -> 0.0986
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 78.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0892` `goal_rate=0.1164` `scorer_weight=0.0981`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0939` `assist_rate=0.0` `provider_weight=0.0789`	-

Mario Soriano M 85 0 0.04 0.04 ok 1 0.9 7.2 53.2 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9962, quality 0.470)	`market_value_eur=5600000` `quality_factor=0.4695` `boost_factor=0.9962` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0387)	`blend_weight=0.0387` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9397` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.5408 -> 2.4716 fouls: 0.9242 -> 0.903 wasFouled: 1.5581 -> 1.5414 interceptionWon: 0.7633 -> 0.7483 wonTackle: 0.4325 -> 0.4449 goalAssist: 0.1061 -> 0.1165 onTargetScoringAttempt: 0.2602 -> 0.2501
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Jan Oblak', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.251, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.7523, 'skill_edge': -0.1085, 'height_edge': -0.06, 'attacker_skill': 0.4695, 'defender_skill': 0.7107, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Jan Oblak', 'market_value': 16000000, 'role': 'GK', 'price_index': 0.55, 'adjusted_quality': 0.7107}], 'xg_override': 0.0521}	aerialWon: 0.2818 -> 0.6 totalShots: 1.1835 -> 0.8903 shotOffTarget: 0.9259 -> 0.6966 onTargetScoringAttempt: 0.2501 -> 0.1882 expectedGoalsOnTarget: 0.1231 -> 0.0926 goals: 0.0771 -> 0.058 expectedGoals: 0.0693 -> 0.0521
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0521 -> 0.0449 expected_assists: 0.1492 -> 0.1103
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 75.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0439` `goal_rate=0.058` `scorer_weight=0.0475`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1044` `assist_rate=0.1165` `provider_weight=0.0922`	-

Diego Villares M 80 0 0.04 0.04 ok 1 0.3 6.9 29.0 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9899, quality 0.437)	`market_value_eur=1000000` `quality_factor=0.4374` `boost_factor=0.9899` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0152)	`blend_weight=0.0152` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.8936` `prior_reliability=0.0467` `competition=La Liga`	wonTackle: 0.5702 -> 0.6003 totalShots: 0.8791 -> 0.8658 wasFouled: 0.4538 -> 0.4469 fouls: 0.9401 -> 0.9452
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Morten Hjulmand', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.241, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.737, 'skill_edge': -0.1829, 'height_edge': 0.004, 'attacker_skill': 0.4374, 'defender_skill': 0.8439, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Morten Hjulmand', 'market_value': 48000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8439}], 'xg_override': 0.0485}	aerialWon: 0.7476 -> 1.2 totalShots: 0.8754 -> 0.6452 shotOffTarget: 0.6451 -> 0.4754 onTargetScoringAttempt: 0.2303 -> 0.1697 expectedGoalsOnTarget: 0.1219 -> 0.0898 expectedGoals: 0.0658 -> 0.0485 goals: 0.0618 -> 0.0455
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0485 -> 0.0418 expected_assists: 0.0571 -> 0.0422
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 79.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0409` `goal_rate=0.0455` `scorer_weight=0.0405`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0413` `assist_rate=0.0599` `provider_weight=0.0433`	-

Lorenzo Amatucci M 89 0 0.02 - n/a 0 0.0 6.9 48.7 10 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0026, quality 0.526)	`market_value_eur=10300000` `quality_factor=0.526` `boost_factor=1.0026` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0542)	`blend_weight=0.0542` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9889` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 1.2782 -> 1.2268 wonTackle: 1.2507 -> 1.2901 fouls: 2.168 -> 2.1398 totalShots: 0.5015 -> 0.4743 goalAssist: 0.0551 -> 0.07 onTargetScoringAttempt: 0.1314 -> 0.1243
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Morten Hjulmand', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.234, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7271, 'skill_edge': -0.1336, 'height_edge': -0.052, 'attacker_skill': 0.547, 'defender_skill': 0.8439, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Morten Hjulmand', 'market_value': 48000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8439}], 'xg_override': 0.0245}	aerialWon: 1.5629 -> 0.8 totalShots: 0.4944 -> 0.3595 shotOffTarget: 0.3701 -> 0.2691 onTargetScoringAttempt: 0.1243 -> 0.0904 goals: 0.0451 -> 0.0328 expectedGoals: 0.0337 -> 0.0245
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0414 -> 0.0306
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 73.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0209` `goal_rate=0.0328` `scorer_weight=0.0235`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0301` `assist_rate=0.07` `provider_weight=0.0382`	-

Giacomo Quagliata D 88 0 0.03 0.02 35% 0 0.5 6.7 48.5 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9942, quality 0.451)	`market_value_eur=4099999` `quality_factor=0.4511` `boost_factor=0.9942` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0464)	`blend_weight=0.0464` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9829` `prior_reliability=0.2` `competition=La Liga`	totalCross: 3.7252 -> 3.6587 totalShots: 0.5042 -> 0.4808 wonTackle: 0.7983 -> 0.7764 onTargetScoringAttempt: 0.3309 -> 0.3155 interceptionWon: 1.0296 -> 1.0426 fouls: 1.5137 -> 1.5043
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Ademola Lookman', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.066 -> 0.0488
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 73.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0279` `goal_rate=0.0` `scorer_weight=0.0226`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0476` `assist_rate=0.0` `provider_weight=0.039`	-

Lucas Noubi D 90 0 0.00 - n/a 1 0.0 6.9 27.9 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9901, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.9901` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0650)	`blend_weight=0.065` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	totalShots: 0.581 -> 0.5432 interceptionWon: 1.1855 -> 1.2168 wasFouled: 1.1043 -> 1.0759 fouls: 1.1881 -> 1.1759 wonTackle: 0.86 -> 0.8691
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Julián Alvarez', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 73.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0075` `assist_rate=0.0` `provider_weight=0.0062`	-

José María Giménez D 84 0 0.06 0.04 48% 1 0.5 6.9 46.6 25 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9983, quality 0.472)	`market_value_eur=5800000` `quality_factor=0.472` `boost_factor=0.9983` `reference_quality=0.505` `history_matches=24` `history_shrink=0.1724`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0030)	`blend_weight=0.003` `history_matches=24` `season_overlap_discount=1.0` `per90_to_match_factor=0.9347` `prior_reliability=0.0267` `competition=La Liga`	fouls: 1.2257 -> 1.236
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alejandro Grimaldo', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0719 -> 0.0619 expected_assists: 0.0212 -> 0.0157
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 82.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.06` `goal_rate=0.0` `scorer_weight=0.0495`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0156` `assist_rate=0.0426` `provider_weight=0.0196`	-

Ximo Navarro D 80 0 0.03 0.02 36% 0 0.3 6.7 43.1 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.437)	`market_value_eur=95000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0483)	`blend_weight=0.0483` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.8916` `prior_reliability=0.1933` `competition=La Liga`	fouls: 0.3455 -> 0.3734 wonTackle: 1.1292 -> 1.1043 totalCross: 1.1315 -> 1.1511 wasFouled: 0.6001 -> 0.6157 interceptionWon: 0.9878 -> 0.9995 totalShots: 0.4357 -> 0.4444
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Julián Alvarez', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 72.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0283` `goal_rate=0.0` `scorer_weight=0.023`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0093` `assist_rate=0.0` `provider_weight=0.0074`	-

Leo Román G 90 0 0.00 - n/a 0.0 7.0 63.9 33 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0001, quality 0.507)	`market_value_eur=8700000` `quality_factor=0.5071` `boost_factor=1.0001` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0138)	`blend_weight=0.0138` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Ademola Lookman, Julián Alvarez', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 2.657}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	shots_faced: 25.2 -> 27.6 expected_saves: 6.16 -> 6.76 high_pressure_saves: 2.13 -> 2.32
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=0.6442`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.457`	-

Luismi Cruz F 69 0 0.08 0.05 55% 1 0.5 6.9 47.1 22 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9928, quality 0.437)	`market_value_eur=2100000` `quality_factor=0.4374` `boost_factor=0.9928` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Marc Pubill, Dávid Hancko', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.6463, 'skill_edge': -0.1806, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.8388, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Marc Pubill', 'market_value': 48000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8608}, {'player': 'Dávid Hancko', 'market_value': 36000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8168}], 'xg_override': 0.0949}	totalShots: 1.1487 -> 0.7424 shotOffTarget: 0.7253 -> 0.4688 onTargetScoringAttempt: 0.4234 -> 0.2736 expectedGoals: 0.1468 -> 0.0949 goals: 0.1383 -> 0.0894 expectedGoalsOnTarget: 0.1112 -> 0.0719
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.66 (squad xG sum 0.7603, xG scale 0.8616, xA scale 0.7390, team xA 0.52 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.655` `squad_xg_sum=0.7603` `squad_xa_sum=0.709` `team_expected_assists=0.524` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0949 -> 0.0818 expected_assists: 0.1163 -> 0.0859
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 74.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0785` `goal_rate=0.0894` `scorer_weight=0.0787`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0823` `assist_rate=0.0827` `provider_weight=0.0687`	-

Team totals 0 0.66 10 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Álvaro Ferllo	G	4.4m	10.9%	Market-value substitute prior
Bright Ede	D	13.7m	30.6%	Market-value substitute prior
Adrià Altimira	D	13.6m	29.9%	Market-value substitute prior
Marc Casadó	M	22.6m	52.9%	Market-value substitute prior
Angeliño	M	22.0m	50.1%	Market-value substitute prior
Jonathan Asp Jensen	F	25.4m	56.5%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~54% possession expected (Pablo Barrios vs Lorenzo Amatucci). Total antagonist xG — Home: 1.36, Away: 0.52. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 54.0% / 46.0%, dominance ratio 0.62, key duel: Pablo Barrios vs Lorenzo Amatucci

Alejandro Grimaldo xG 0.18Julián Alvarez xG 0.29Ademola Lookman xG 0.33Mario Soriano xG 0.05Yeremay Hernández xG 0.11Bil Nsongo xG 0.19

Summary

Antagonist matchup analysis for Atlético Madrid vs Deportivo. Most likely scoreline: 2-0. Lambdas derived from 7 home and 6 away individual player duels. Head-to-head: Atlético Madrid 7W-3D-0L vs Deportivo over 10 meetings.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Home midfield dominates with ~54% possession expected (Pablo Barrios vs Lorenzo Amatucci). Total antagonist xG — Home: 1.36, Away: 0.52. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Rayo Vallecano vs Elche

LaLiga · 20261024 · 4-2-3-1 vs 4-2-3-1

Predicted 1-1Winner: DrawWinning H 1-0 (11.6%)Winning A 0-1 (10.0%)Confidence 0.7λ home/away 1.29 / 1.11Most-likely P 13.1%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Rayo Vallecano vs Elche. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 1.286, Away 1.111). Final calibrated Poisson lambdas: Home 1.286, Away 1.111 (most likely score 1-1).

Home Starters 11/11 XGBoost (5 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.29 / 1.11 Final λ (H/A) 1.29 / 1.11

FBref Team Priors: Rayo Vallecano (Gls/90: 1.3333333333333333, GA/90: 1.33 → E[λ]: 0.988) vs Elche (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.985) | Blend Weight: 0.228

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Rayo Vallecano	Elche
League position	13.00	18.00
Points per game	1.22	1.01
Attack index	0.99	0.87
Defense (concede) index	1.05	1.15
Form multiplier	1.01	0.99
Standing λ multiplier	1.02	1.00

Lambda decomposition (how the goal rates were built)

Stage	Rayo Vallecano λ	Elche λ
FBref Squad Prior E[λ] (weight 0.228)	0.988	0.985
Pre-competitive-floor	1.286	1.111
Pre-calibration (Micro-duels)	1.286	1.111
Final λ	1.286	1.111

competition calibration scale 1.0competition observed total goals 0.0quality gap applied Falsemismatch score pressure applied Falsecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
1-1	13.1%
1-0	11.6%
0-1	10.0%
0-0	9.2%
2-1	8.4%

Home win	40.4%
Draw	27.8%
Away win	31.9%
Over 2.5	43.0%
BTTS yes	48.7%

Pregame fair line — favorite Rayo Vallecano (40.4%), fair total 2.40, fair spread 0.17

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Rayo Vallecano — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Mujaid Sadick D 85 0 0.00 - n/a 0 0.0 6.8 33.0 8 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.458)	`market_value_eur=4700000` `quality_factor=0.4585` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=4` `history_shrink=0.5556`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Fernando Niño', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 84.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0053` `assist_rate=0.0` `provider_weight=0.0049`	-

Florian Lejeune D 90 0 0.09 0.06 56% 1 1.4 7.1 61.4 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9979, quality 0.437)	`market_value_eur=1700000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0133)	`blend_weight=0.0133` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.1718 -> 1.1916 wonTackle: 0.9638 -> 0.9775 totalShots: 1.1128 -> 1.1202
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Fernando Niño', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.0751 -> 0.0943
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 79.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.09` `goal_rate=0.0555` `scorer_weight=0.0795`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0159` `assist_rate=0.011` `provider_weight=0.0156`	-

Iván Balliu D 80 0 0.03 0.00 3416% 0 0.0 6.6 27.5 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9961, quality 0.437)	`market_value_eur=1100000` `quality_factor=0.4374` `boost_factor=0.9961` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0167)	`blend_weight=0.0167` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.8852` `prior_reliability=0.1333` `competition=La Liga`	totalCross: 0.8623 -> 0.8553 totalShots: 0.3318 -> 0.3263
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Lucas Cepeda', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.0232 -> 0.0291 expected_assists: 0.037 -> 0.0465
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 18 by projected rating, fifa_overall 74.0)	`match_squad_rank=18` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0287` `goal_rate=0.0` `scorer_weight=0.0233`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0454` `assist_rate=0.0` `provider_weight=0.0372`	-

Emil Audero G 90 0 0.00 - n/a 0.0 6.9 34.0 8 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9887, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9887` `reference_quality=0.505` `history_matches=4` `history_shrink=0.5556`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Fernando Niño, Lucas Cepeda', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.1114}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 79.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3418`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.8581`	-

Adrià Pedrosa D 86 0 0.05 0.02 217% 1 0.4 6.7 45.5 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9973, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0040)	`blend_weight=0.004` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.9541` `prior_reliability=0.0467` `competition=La Liga`	fouls: 1.1654 -> 1.1716
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Thomas Lemar', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.0383 -> 0.0481 expected_assists: 0.1302 -> 0.1635
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 74.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.047` `goal_rate=0.1225` `scorer_weight=0.0601`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.1508` `assist_rate=0.144` `provider_weight=0.176`	-

Unai López M 80 0 0.07 0.03 190% 1 0.6 7.1 51.6 28 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9975, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0143)	`blend_weight=0.0143` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.8883` `prior_reliability=0.18` `competition=La Liga`	totalShots: 1.0254 -> 1.0155 fouls: 1.1166 -> 1.1241
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Matías Dituro', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.36, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9118, 'skill_edge': 0.0, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Matías Dituro', 'market_value': 105000, 'role': 'GK', 'price_index': 0.55, 'adjusted_quality': 0.4374}], 'xg_override': 0.0585}	aerialWon: 0.3743 -> 0.8 totalShots: 1.0259 -> 0.9354 shotOffTarget: 0.7289 -> 0.6646 onTargetScoringAttempt: 0.297 -> 0.2708 goals: 0.0848 -> 0.0773 expectedGoals: 0.0642 -> 0.0585
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.0585 -> 0.0735 expected_assists: 0.1442 -> 0.1811
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 76.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0709` `goal_rate=0.0773` `scorer_weight=0.0862`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1656` `assist_rate=0.1158` `provider_weight=0.1546`	-

Pathé Ismaël Ciss M 90 0 0.06 0.08 ok 1 0.5 6.9 62.3 30 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9976, quality 0.437)	`market_value_eur=1600000` `quality_factor=0.4374` `boost_factor=0.9976` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Javi Morcillo', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.42, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0, 'skill_edge': 0.0, 'height_edge': 0.0, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Javi Morcillo', 'market_value': 2100000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0494}`	aerialWon: 1.7013 -> 1.1
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.0494 -> 0.0621 expected_assists: 0.0319 -> 0.0401
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 82.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0602` `goal_rate=0.0526` `scorer_weight=0.0641`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0393` `assist_rate=0.0495` `provider_weight=0.0487`	-

Giorgi Tsitaishvili F 81 0 0.17 0.10 81% 2 0.9 6.7 31.9 14 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9899, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9899` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Roy Revivo, Buba Sangaré', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8993, 'skill_edge': -0.0185, 'height_edge': -0.05, 'attacker_skill': 0.4374, 'defender_skill': 0.4785, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Roy Revivo', 'market_value': 4600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4761}, {'player': 'Buba Sangaré', 'market_value': 4900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4809}], 'xg_override': 0.1388}	totalShots: 1.5468 -> 1.391 shotOffTarget: 0.9573 -> 0.8609 onTargetScoringAttempt: 0.5894 -> 0.53 bigChanceMissed: 0.2126 -> 0.1912 goals: 0.2012 -> 0.1809 expectedGoals: 0.1543 -> 0.1388 expectedGoalsOnTarget: 0.0599 -> 0.0539
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.1388 -> 0.1743 expected_assists: 0.0779 -> 0.0978
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 78.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.16` `goal_rate=0.1809` `scorer_weight=0.2132`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0932` `assist_rate=0.0` `provider_weight=0.0782`	-

Alemão F 75 0 0.28 0.09 207% 2 0.6 6.7 44.5 31 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9980, quality 0.455)	`market_value_eur=4400000` `quality_factor=0.4548` `boost_factor=0.998` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Roy Revivo, Buba Sangaré', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.183, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9755, 'skill_edge': -0.0107, 'height_edge': -0.006, 'attacker_skill': 0.4548, 'defender_skill': 0.4785, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Roy Revivo', 'market_value': 4600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4761}, {'player': 'Buba Sangaré', 'market_value': 4900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4809}], 'xg_override': 0.2204}	totalShots: 1.6564 -> 1.6158 shotOffTarget: 0.9795 -> 0.9555 onTargetScoringAttempt: 0.6768 -> 0.6602 bigChanceMissed: 0.3269 -> 0.3189 expectedGoals: 0.2259 -> 0.2204 goals: 0.2058 -> 0.2008
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.2204 -> 0.2768 expected_assists: 0.0274 -> 0.0344
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 74.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2418` `goal_rate=0.2008` `scorer_weight=0.2567`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0338` `assist_rate=0.0` `provider_weight=0.0275`	-

Álvaro García F 80 1 0.28 0.18 60% 2 1.1 6.8 54.4 35 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0106)	`blend_weight=0.0106` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.8939` `prior_reliability=0.1467` `competition=La Liga`	totalShots: 1.9809 -> 1.9686 totalCross: 3.3337 -> 3.3242 fouls: 0.4681 -> 0.4761 totalOffside: 0.3058 -> 0.3112
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Roy Revivo, Buba Sangaré', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8846, 'skill_edge': -0.0185, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.4785, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Roy Revivo', 'market_value': 4600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4761}, {'player': 'Buba Sangaré', 'market_value': 4900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4809}], 'xg_override': 0.2243}	totalShots: 1.9776 -> 1.7494 shotOffTarget: 1.2576 -> 1.1125 onTargetScoringAttempt: 0.72 -> 0.6369 expectedGoalsOnTarget: 0.3353 -> 0.2966 bigChanceMissed: 0.3047 -> 0.2695 goals: 0.278 -> 0.2459 expectedGoals: 0.2536 -> 0.2243
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.2243 -> 0.2819 expected_assists: 0.0772 -> 0.097
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 81.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2457` `goal_rate=0.2459` `scorer_weight=0.3041`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0924` `assist_rate=0.2497` `provider_weight=0.1212`	-

Isi Palazón M 67 0 0.14 0.11 36% 1 1.2 6.8 55.7 22 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9974, quality 0.437)	`market_value_eur=3000000` `quality_factor=0.4374` `boost_factor=0.9974` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Javi Morcillo', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.367, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.922, 'skill_edge': 0.003, 'height_edge': -0.056, 'attacker_skill': 0.444, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Javi Morcillo', 'market_value': 2100000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.1141}	totalShots: 1.5077 -> 1.3901 shotOffTarget: 1.0291 -> 0.9488 aerialWon: 0.8711 -> 0.8 onTargetScoringAttempt: 0.4786 -> 0.4413 bigChanceMissed: 0.1481 -> 0.1365 expectedGoals: 0.1238 -> 0.1141 goals: 0.1183 -> 0.1091 expectedGoalsOnTarget: 0.0729 -> 0.0672
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.29 (squad xG sum 1.0238, xG scale 1.2561, xA scale 1.2561, team xA 0.88 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.286` `squad_xg_sum=1.0238` `squad_xa_sum=0.7033` `team_expected_assists=0.8834` `team_xa_to_xg_ratio=0.6869`	expected_goals: 0.1141 -> 0.1433 expected_assists: 0.107 -> 0.1344
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 79.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1335` `goal_rate=0.1091` `scorer_weight=0.1389`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1258` `assist_rate=0.0926` `provider_weight=0.1221`	-

Team totals 1 1.29 13 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Augusto Batalla	G	4.5m	13.4%	Market-value substitute prior
Andrei Rațiu	D	14.4m	23.4%	Market-value substitute prior
Abdul Mumin	D	13.6m	29.9%	Market-value substitute prior
Pedro Díaz	M	23.1m	69.2%	Market-value substitute prior
Óscar Valentín	M	29.7m	43.5%	Market-value substitute prior
Jorge de Frutos	F	25.7m	57.6%	Market-value substitute prior

Elche — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Fernando Niño F 75 1 0.41 0.28 47% 2 1.2 6.9 58.0 11 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9936, quality 0.445)	`market_value_eur=3600000` `quality_factor=0.4449` `boost_factor=0.9936` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0387)	`blend_weight=0.0387` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8302` `prior_reliability=0.1667` `competition=La Liga`	totalShots: 2.086 -> 2.0564 fouls: 0.8201 -> 0.8012 totalOffside: 0.1347 -> 0.1295
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mujaid Sadick, Florian Lejeune', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.204, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0063, 'skill_edge': -0.0057, 'height_edge': 0.01, 'attacker_skill': 0.4449, 'defender_skill': 0.4576, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mujaid Sadick', 'market_value': 4700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4777}, {'player': 'Florian Lejeune', 'market_value': 1700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.3468}	totalShots: 2.0831 -> 2.0963 onTargetScoringAttempt: 1.0585 -> 1.0652 shotOffTarget: 1.0246 -> 1.0311
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.3468 -> 0.4105
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 81.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3367` `goal_rate=0.4068` `scorer_weight=0.4726`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0457` `assist_rate=0.0` `provider_weight=0.0374`	-

Germán Valera F 85 0 0.11 0.04 195% 1 0.5 6.8 58.3 42 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9992, quality 0.477)	`market_value_eur=6200000` `quality_factor=0.4769` `boost_factor=0.9992` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mujaid Sadick, Florian Lejeune', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9246, 'skill_edge': 0.0087, 'height_edge': -0.06, 'attacker_skill': 0.4769, 'defender_skill': 0.4576, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mujaid Sadick', 'market_value': 4700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4777}, {'player': 'Florian Lejeune', 'market_value': 1700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.094}	totalShots: 1.0171 -> 0.9404 shotOffTarget: 0.6366 -> 0.5886 onTargetScoringAttempt: 0.3805 -> 0.3518 goals: 0.1407 -> 0.1301 expectedGoals: 0.1017 -> 0.094 bigChanceMissed: 0.0669 -> 0.0619
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.094 -> 0.1112 expected_assists: 0.1524 -> 0.1697
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 82.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1052` `goal_rate=0.1301` `scorer_weight=0.139`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1561` `assist_rate=0.0411` `provider_weight=0.1358`	-

Lucas Cepeda F 77 0 0.13 0.05 184% 2 0.8 6.9 43.1 30 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9958, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9958` `reference_quality=0.505` `history_matches=19` `history_shrink=0.2083`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0081)	`blend_weight=0.0081` `history_matches=19` `season_overlap_discount=1.0` `per90_to_match_factor=0.8544` `prior_reliability=0.06` `competition=La Liga`	totalCross: 1.5309 -> 1.5647 totalShots: 1.4 -> 1.4277 fouls: 0.8041 -> 0.8207 interceptionWon: 0.329 -> 0.3418 wasFouled: 2.3268 -> 2.3156 onTargetScoringAttempt: 0.5487 -> 0.5599 wonTackle: 1.0264 -> 1.0181 goalAssist: 0.0 -> 0.0077
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mujaid Sadick, Florian Lejeune', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9249, 'skill_edge': -0.0091, 'height_edge': -0.042, 'attacker_skill': 0.4374, 'defender_skill': 0.4576, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mujaid Sadick', 'market_value': 4700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4777}, {'player': 'Florian Lejeune', 'market_value': 1700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.1104}	totalShots: 1.4277 -> 1.3205 shotOffTarget: 0.8513 -> 0.7874 onTargetScoringAttempt: 0.5599 -> 0.5179 goals: 0.1645 -> 0.1521 expectedGoals: 0.1194 -> 0.1104
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1104 -> 0.1306 expected_assists: 0.105 -> 0.1169
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 71.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1224` `goal_rate=0.1521` `scorer_weight=0.1633`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1103` `assist_rate=0.0077` `provider_weight=0.0935`	-

Gonzalo Villar M 81 0 0.09 0.03 249% 1 0.4 6.9 53.4 27 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9961, quality 0.437)	`market_value_eur=1700000` `quality_factor=0.4374` `boost_factor=0.9961` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0250)	`blend_weight=0.025` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.899` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 2.1057 -> 2.1579 totalCross: 1.2925 -> 1.3276 fouls: 1.6609 -> 1.6793 onTargetScoringAttempt: 0.2615 -> 0.2774 totalShots: 0.7097 -> 0.7218 goalAssist: 0.0876 -> 0.0929
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pathé Ismaël Ciss, Isi Palazón', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.259, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0272, 'skill_edge': -0.0015, 'height_edge': 0.02, 'attacker_skill': 0.4374, 'defender_skill': 0.4407, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Pathé Ismaël Ciss', 'market_value': 1600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}, {'player': 'Isi Palazón', 'market_value': 3000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.444}], 'xg_override': 0.0745}	aerialWon: 0.7743 -> 1.1 totalShots: 0.7255 -> 0.7452 shotOffTarget: 0.4481 -> 0.4603 onTargetScoringAttempt: 0.2774 -> 0.2849
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0745 -> 0.0881 expected_assists: 0.0794 -> 0.0884
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 72.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0843` `goal_rate=0.0818` `scorer_weight=0.0933`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0846` `assist_rate=0.0929` `provider_weight=0.0976`	-

Javi Morcillo M 87 0 0.04 0.01 178% 1 0.2 6.7 41.3 21 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9940, quality 0.437)	`market_value_eur=2100000` `quality_factor=0.4374` `boost_factor=0.994` `reference_quality=0.505` `history_matches=12` `history_shrink=0.2941`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0051)	`blend_weight=0.0051` `history_matches=12` `season_overlap_discount=1.0` `per90_to_match_factor=0.9649` `prior_reliability=0.0267` `competition=La Liga`	fouls: 0.6484 -> 0.6574 wonTackle: 1.1736 -> 1.1799 interceptionWon: 1.0933 -> 1.0877
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pathé Ismaël Ciss', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.42, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0, 'skill_edge': 0.0, 'height_edge': 0.0, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pathé Ismaël Ciss', 'market_value': 1600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0321}	aerialWon: 0.847 -> 1.1
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0321 -> 0.038
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 79.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0373` `goal_rate=0.0417` `scorer_weight=0.0424`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0291` `assist_rate=0.0384` `provider_weight=0.0341`	-

Roy Revivo D 88 0 0.01 0.02 45% 1 0.2 6.8 50.9 8 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9935, quality 0.457)	`market_value_eur=4600000` `quality_factor=0.4572` `boost_factor=0.9935` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alemão', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.1551 -> 0.1728
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 80.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.011` `goal_rate=0.0` `scorer_weight=0.0093`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.1587` `assist_rate=0.3871` `provider_weight=0.216`	-

Federico Redondo M 68 0 0.03 0.01 561% 0 0.1 6.8 33.2 34 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9954, quality 0.437)	`market_value_eur=2400000` `quality_factor=0.4374` `boost_factor=0.9954` `reference_quality=0.505` `history_matches=17` `history_shrink=0.2273`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0148)	`blend_weight=0.0148` `history_matches=17` `season_overlap_discount=1.0` `per90_to_match_factor=0.7547` `prior_reliability=0.1` `competition=La Liga`	fouls: 0.9905 -> 0.9833
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pathé Ismaël Ciss', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.44, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0294, 'skill_edge': 0.0, 'height_edge': 0.02, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pathé Ismaël Ciss', 'market_value': 1600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0283}	aerialWon: 0.1472 -> 1.2 totalShots: 0.4631 -> 0.4767 shotOffTarget: 0.353 -> 0.3634
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0283 -> 0.0335
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 70.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0329` `goal_rate=0.0388` `scorer_weight=0.038`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0375` `assist_rate=0.0384` `provider_weight=0.0401`	-

Víctor Chust D 90 0 0.05 0.02 103% 1 0.4 6.9 63.9 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0144)	`blend_weight=0.0144` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.995` `prior_reliability=0.2` `competition=La Liga`	totalCross: 1.085 -> 1.0981 wonTackle: 0.944 -> 0.9495
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alemão', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0384 -> 0.0454
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 74.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0444` `goal_rate=0.0413` `scorer_weight=0.0469`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0388` `assist_rate=0.0658` `provider_weight=0.0495`	-

Buba Sangaré D 74 0 0.01 0.01 ok 0 0.1 6.6 52.1 25 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9974, quality 0.461)	`market_value_eur=4900000` `quality_factor=0.4609` `boost_factor=0.9974` `reference_quality=0.505` `history_matches=20` `history_shrink=0.2`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0251)	`blend_weight=0.0251` `history_matches=20` `season_overlap_discount=1.0` `per90_to_match_factor=0.8246` `prior_reliability=0.1933` `competition=La Liga`	wonTackle: 0.9869 -> 1.005 totalCross: 0.9656 -> 0.9556 interceptionWon: 0.6732 -> 0.6634 fouls: 1.1181 -> 1.1257 goals: 0.0717 -> 0.077 onTargetScoringAttempt: 0.0717 -> 0.0769
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alemão', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 69.0)	`match_squad_rank=17` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0052` `goal_rate=0.0769` `scorer_weight=0.0065`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.017` `assist_rate=0.0` `provider_weight=0.0137`	-

Matías Dituro G 90 0 0.00 - n/a 0.0 7.1 55.7 32 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9972, quality 0.437)	`market_value_eur=105000` `quality_factor=0.4374` `boost_factor=0.9972` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0181)	`blend_weight=0.0181` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.8862 -> 2.8762
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Álvaro García, Alemão', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2861}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 76.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3027`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.8565`	-

Thomas Lemar M 72 0 0.08 0.07 ok 1 0.6 7.0 61.7 28 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9973, quality 0.437)	`market_value_eur=1900000` `quality_factor=0.4374` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Adrià Pedrosa', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.451, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9577, 'skill_edge': -0.0048, 'height_edge': -0.024, 'attacker_skill': 0.4374, 'defender_skill': 0.4481, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Adrià Pedrosa', 'market_value': 2700000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4481}], 'xg_override': 0.0712}	aerialWon: 0.0237 -> 0.8 totalShots: 1.0005 -> 0.9582 shotOffTarget: 0.6506 -> 0.6231 onTargetScoringAttempt: 0.3499 -> 0.3351 expectedGoalsOnTarget: 0.1251 -> 0.1198
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.11 (squad xG sum 0.9390, xG scale 1.1832, xA scale 1.1135, team xA 0.89 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.111` `squad_xg_sum=0.939` `squad_xa_sum=0.7982` `team_expected_assists=0.8888` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0712 -> 0.0842 expected_assists: 0.1146 -> 0.1276
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 77.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0808` `goal_rate=0.0938` `scorer_weight=0.0999`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1198` `assist_rate=0.0855` `provider_weight=0.105`	-

Team totals 1 1.11 13 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Iñaki Peña	G	4.4m	11.0%	Market-value substitute prior
Kevin Lomónaco	D	13.8m	31.0%	Market-value substitute prior
Rubén Sánchez	D	13.6m	29.9%	Market-value substitute prior
Martim Neto	M	24.8m	50.0%	Market-value substitute prior
Marc Aguado	M	22.0m	30.8%	Market-value substitute prior
Facundo Buonanotte	F	26.4m	53.4%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Isi Palazón vs Federico Redondo will be the pivotal duel. Total antagonist xG — Home: 0.81, Away: 0.76. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.0% / 50.0%, dominance ratio 0.49, key duel: Isi Palazón vs Federico Redondo

Unai López xG 0.06Alemão xG 0.22Giorgi Tsitaishvili xG 0.14Thomas Lemar xG 0.07Gonzalo Villar xG 0.07Fernando Niño xG 0.35

Summary

Antagonist matchup analysis for Rayo Vallecano vs Elche. Most likely scoreline: 1-1. Lambdas derived from 6 home and 7 away individual player duels. Head-to-head: Rayo Vallecano 4W-2D-4L vs Elche over 10 meetings.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Isi Palazón vs Federico Redondo will be the pivotal duel. Total antagonist xG — Home: 0.81, Away: 0.76. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Racing Club vs Espanyol

LaLiga · 20261024 · 4-2-3-1 vs 5-4-1

Predicted 1-1Winner: DrawWinning H 1-0 (8.1%)Winning A 0-1 (9.0%)Confidence 0.7λ home/away 1.31 / 1.46Most-likely P 12.1%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Racing Club vs Espanyol. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 5-4-1 (duel lambdas: Home 1.303, Away 1.470). Final calibrated Poisson lambdas: Home 1.312, Away 1.460 (most likely score 1-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.30 / 1.47 Final λ (H/A) 1.31 / 1.46

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Racing Club	Espanyol
League position	16.00	15.00
Points per game	1.08	1.08
Attack index	1.02	0.87
Defense (concede) index	0.90	1.42
Form multiplier	1.00	1.00
Standing λ multiplier	0.97	1.09

Lambda decomposition (how the goal rates were built)

Stage	Racing Club λ	Espanyol λ
Pre-competitive-floor	1.312	1.460
Pre-calibration (Micro-duels)	1.303	1.470
Final λ	1.312	1.460

Scoreline distribution & markets

Top 5 scorelines	P
1-1	12.1%
0-1	9.0%
1-2	8.7%
1-0	8.1%
2-1	7.9%

Home win	33.8%
Draw	25.6%
Away win	40.6%
Over 2.5	52.4%
BTTS yes	56.2%

Pregame fair line — favorite Espanyol (40.6%), fair total 2.77, fair spread -0.15

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Racing Club — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Yassir Zabiri F 81 1 0.48 0.33 44% 3 1.5 6.8 53.7 12 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0156, quality 0.650)	`market_value_eur=22000000` `quality_factor=0.6503` `boost_factor=1.0156` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0201)	`blend_weight=0.0201` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9049` `prior_reliability=0.0867` `competition=La Liga`	goals: 0.4029 -> 0.4368 totalOffside: 0.2588 -> 0.2816 onTargetScoringAttempt: 1.0145 -> 1.0362 totalShots: 2.4291 -> 2.4503 wasFouled: 0.6991 -> 0.685 fouls: 1.6086 -> 1.6183 wonTackle: 0.4055 -> 0.3973
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Leandro Cabrera, Vanja Drkušić', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.26, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0879, 'skill_edge': 0.0838, 'height_edge': -0.024, 'attacker_skill': 0.6503, 'defender_skill': 0.464, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Vanja Drkušić', 'market_value': 5500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4907}], 'xg_override': 0.4102}	totalShots: 2.4508 -> 2.6662 shotOffTarget: 1.4146 -> 1.5389 onTargetScoringAttempt: 1.0362 -> 1.1273 expectedGoalsOnTarget: 0.5924 -> 0.6445 goals: 0.4368 -> 0.4752 expectedGoals: 0.3771 -> 0.4102
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	expected_goals: 0.4102 -> 0.4785 expected_assists: 0.0365 -> 0.0426
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 66.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3803` `goal_rate=0.4752` `scorer_weight=0.5461`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0417` `assist_rate=0.0` `provider_weight=0.0341`	-

Iñigo Vicente F 86 0 0.10 0.04 170% 1 0.5 7.1 53.5 22 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9975, quality 0.482)	`market_value_eur=6600000` `quality_factor=0.4818` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0433)	`blend_weight=0.0433` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.954` `prior_reliability=0.1867` `competition=La Liga`	totalCross: 5.3659 -> 5.2515 totalShots: 0.953 -> 0.9266 interceptionWon: 0.8246 -> 0.8036 wonTackle: 1.1227 -> 1.1036 onTargetScoringAttempt: 0.3828 -> 0.3662 wasFouled: 2.3061 -> 2.2948 totalOffside: 0.1733 -> 0.1806
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Leandro Cabrera, Vanja Drkušić', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9529, 'skill_edge': 0.008, 'height_edge': -0.04, 'attacker_skill': 0.4818, 'defender_skill': 0.464, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Vanja Drkušić', 'market_value': 5500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4907}], 'xg_override': 0.0844}	totalShots: 0.9364 -> 0.8923 shotOffTarget: 0.5702 -> 0.5433 onTargetScoringAttempt: 0.3662 -> 0.349
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	expected_goals: 0.0844 -> 0.0985 expected_assists: 0.2503 -> 0.2921
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 77.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0938` `goal_rate=0.0907` `scorer_weight=0.1031`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.2533` `assist_rate=0.3902` `provider_weight=0.3651`	-

Sergio Canales F 78 0 0.11 0.10 ok 2 1.8 6.8 53.2 21 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9930, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.993` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0387)	`blend_weight=0.0387` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8682` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.4412 -> 2.3602 totalShots: 1.6812 -> 1.7381 wasFouled: 1.9878 -> 1.9512 wonTackle: 0.6319 -> 0.6074 onTargetScoringAttempt: 0.5576 -> 0.5767 interceptionWon: 0.4066 -> 0.3909 fouls: 0.6698 -> 0.6573 totalOffside: 0.2048 -> 0.1969
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Leandro Cabrera, Vanja Drkušić', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9135, 'skill_edge': -0.0109, 'height_edge': -0.048, 'attacker_skill': 0.4399, 'defender_skill': 0.464, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Vanja Drkušić', 'market_value': 5500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4907}], 'xg_override': 0.0978}	totalShots: 1.7381 -> 1.5878 shotOffTarget: 1.1236 -> 1.0264 onTargetScoringAttempt: 0.5767 -> 0.5268 expectedGoalsOnTarget: 0.1622 -> 0.1482 goals: 0.1325 -> 0.121 expectedGoals: 0.1071 -> 0.0978
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	expected_goals: 0.0978 -> 0.1141 expected_assists: 0.1242 -> 0.1449
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 78.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1078` `goal_rate=0.121` `scorer_weight=0.132`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1349` `assist_rate=0.0` `provider_weight=0.1159`	-

Andrés Martín F 79 0 0.28 0.35 ok 2 1.5 6.9 38.5 14 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9994, quality 0.501)	`market_value_eur=8199999` `quality_factor=0.5011` `boost_factor=0.9994` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0563)	`blend_weight=0.0563` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.8752` `prior_reliability=0.1733` `competition=La Liga`	totalShots: 2.0191 -> 2.073 interceptionWon: 0.9498 -> 0.9721 onTargetScoringAttempt: 0.665 -> 0.6832 totalCross: 3.8228 -> 3.835 fouls: 0.8916 -> 0.8983 goals: 0.2193 -> 0.2259
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Leandro Cabrera, Vanja Drkušić', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9657, 'skill_edge': 0.0167, 'height_edge': -0.04, 'attacker_skill': 0.5011, 'defender_skill': 0.464, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Vanja Drkušić', 'market_value': 5500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4907}], 'xg_override': 0.2407}	totalShots: 2.073 -> 2.0019 shotOffTarget: 1.3541 -> 1.3077 onTargetScoringAttempt: 0.6832 -> 0.6598 bigChanceMissed: 0.6604 -> 0.6377 expectedGoalsOnTarget: 0.6358 -> 0.614 expectedGoals: 0.2492 -> 0.2407 goals: 0.2259 -> 0.2182
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	expected_goals: 0.2407 -> 0.2808 expected_assists: 0.1361 -> 0.1588
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 77.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2448` `goal_rate=0.2182` `scorer_weight=0.2591`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1468` `assist_rate=0.0` `provider_weight=0.127`	-

Iván Martín M 85 0 0.05 0.03 90% 1 0.4 7.0 58.1 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0069)	`blend_weight=0.0069` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9463` `prior_reliability=0.1` `competition=La Liga`	wonTackle: 0.9693 -> 0.98 totalCross: 0.333 -> 0.3394
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Edu Expósito, Pol Lozano, Javier Hernández', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	expected_goals: 0.0446 -> 0.052 expected_assists: 0.071 -> 0.0828
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 77.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0507` `goal_rate=0.0682` `scorer_weight=0.065`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0795` `assist_rate=0.0712` `provider_weight=0.0829`	-

Jorge Salinas D 89 0 0.06 0.03 75% 1 0.3 6.7 48.8 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0000, quality 0.505)	`market_value_eur=8500000` `quality_factor=0.5047` `boost_factor=1.0` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0464)	`blend_weight=0.0464` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9872` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 1.7542 -> 1.7186 fouls: 1.3915 -> 1.3575 interceptionWon: 1.3402 -> 1.3238 totalShots: 0.5731 -> 0.5616 totalCross: 1.4693 -> 1.4775 goalAssist: 0.1266 -> 0.1207
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Omar El Hilali', 'matchup_zone': 'RWB vs LW + LB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	expected_goals: 0.0478 -> 0.0558 expected_assists: 0.114 -> 0.133
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 72.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0543` `goal_rate=0.0` `scorer_weight=0.0446`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1245` `assist_rate=0.1207` `provider_weight=0.1384`	-

Jeanuël Belocian D 90 0 0.03 0.02 44% 1 0.3 6.7 35.4 9 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0076, quality 0.556)	`market_value_eur=12900000` `quality_factor=0.5559` `boost_factor=1.0076` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 71.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0301` `goal_rate=0.0` `scorer_weight=0.0245`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0105` `assist_rate=0.0` `provider_weight=0.009`	-

Pablo Ramón D 85 0 0.01 0.00 145% 0 0.2 6.9 39.3 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9916, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9916` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0325)	`blend_weight=0.0325` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.939` `prior_reliability=0.12` `competition=La Liga`	wonTackle: 0.9878 -> 1.0235 interceptionWon: 1.1301 -> 1.1612 totalShots: 0.4745 -> 0.4591 wasFouled: 1.2948 -> 1.2866 onTargetScoringAttempt: 0.1725 -> 0.1669
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Javier Hernández', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 69.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.006` `goal_rate=0.0` `scorer_weight=0.0054`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0115` `assist_rate=0.0` `provider_weight=0.0097`	-

Alvaro Mantilla D 87 0 0.01 0.01 ok 0 0.2 6.7 42.8 12 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.437)	`market_value_eur=1200000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 77.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0132` `goal_rate=0.0` `scorer_weight=0.0108`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0244` `assist_rate=0.0` `provider_weight=0.0198`	-

Julen Agirrezabala G 90 0 0.00 - n/a 0.0 7.1 40.2 17 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9989, quality 0.481)	`market_value_eur=6500000` `quality_factor=0.4805` `boost_factor=0.9989` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0203)	`blend_weight=0.0203` `history_matches=27` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.7346 -> 2.7468 wasFouled: 0.2586 -> 0.2669
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández, Javier Hernández', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.4702}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	shots_faced: 14.0 -> 13.9 expected_saves: 3.43 -> 3.41 high_pressure_saves: 1.18 -> 1.17
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 82.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3832`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.9828`	-

Matteo Prati M 84 0 0.05 0.01 528% 1 0.3 6.8 40.3 10 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9942, quality 0.462)	`market_value_eur=5000000` `quality_factor=0.4622` `boost_factor=0.9942` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0079)	`blend_weight=0.0079` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.9349` `prior_reliability=0.0267` `competition=La Liga`	fouls: 0.1646 -> 0.1817 interceptionWon: 0.6897 -> 0.7027 wonTackle: 1.4858 -> 1.4741 wasFouled: 0.9249 -> 0.9176
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Pol Lozano', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.31 (squad xG sum 1.1245, xG scale 1.1667, xA scale 1.1667, team xA 0.98 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.312` `squad_xg_sum=1.1245` `squad_xa_sum=0.8366` `team_expected_assists=0.9761` `team_xa_to_xg_ratio=0.744`	expected_goals: 0.0405 -> 0.0473 expected_assists: 0.0395 -> 0.0461
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 72.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0462` `goal_rate=0.0454` `scorer_weight=0.0499`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0451` `assist_rate=0.0647` `provider_weight=0.0576`	-

Team totals 1 1.31 14 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Simon Eriksson	G	4.4m	10.9%	Market-value substitute prior
Facundo González	D	13.6m	29.9%	Market-value substitute prior
Pedro Felipe	D	13.6m	29.9%	Market-value substitute prior
Gustavo Puerta	M	22.7m	32.2%	Market-value substitute prior
André Almeida	M	22.1m	50.6%	Market-value substitute prior
Pablo García	F	25.5m	57.0%	Market-value substitute prior

Espanyol — projected line vs season baseline (5-4-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Edu Expósito M 82 0 0.14 0.08 68% 1 1.4 7.0 65.2 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9985, quality 0.456)	`market_value_eur=4500000` `quality_factor=0.456` `boost_factor=0.9985` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0117)	`blend_weight=0.0117` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9072` `prior_reliability=0.18` `competition=La Liga`	totalCross: 3.6204 -> 3.5898 totalShots: 1.2737 -> 1.2945
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Iván Martín', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.448, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9973, 'skill_edge': 0.0101, 'height_edge': -0.012, 'attacker_skill': 0.4622, 'defender_skill': 0.4396, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Iván Martín', 'market_value': 2700000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4396}], 'xg_override': 0.1068}	aerialWon: 0.905 -> 0.9
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_goals: 0.1068 -> 0.1407 expected_assists: 0.15 -> 0.1975
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 77.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1313` `goal_rate=0.1155` `scorer_weight=0.1485`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1792` `assist_rate=0.1021` `provider_weight=0.158`	-

Javier Hernández M 77 0 0.20 0.08 164% 2 1.1 6.8 54.8 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9972, quality 0.479)	`market_value_eur=6400000` `quality_factor=0.4793` `boost_factor=0.9972` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0387)	`blend_weight=0.0387` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8594` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.0138 -> 1.9492 wasFouled: 1.2904 -> 1.3336 fouls: 1.7226 -> 1.7624 goalAssist: 0.2242 -> 0.2554 totalShots: 1.6947 -> 1.6694 interceptionWon: 0.4909 -> 0.4719 onTargetScoringAttempt: 0.5692 -> 0.5605 wonTackle: 0.4748 -> 0.483
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pablo Ramón', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel', 'duel_win_rate': 0.439, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9687, 'skill_edge': 0.0227, 'height_edge': -0.044, 'attacker_skill': 0.488, 'defender_skill': 0.4374, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Pablo Ramón', 'market_value': 1500000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.1515}	aerialWon: 0.1654 -> 0.9 totalShots: 1.686 -> 1.6333 shotOffTarget: 1.1255 -> 1.0903 onTargetScoringAttempt: 0.5605 -> 0.543
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_goals: 0.1515 -> 0.1995 expected_assists: 0.128 -> 0.1686
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 86.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1809` `goal_rate=0.1388` `scorer_weight=0.1869`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.1552` `assist_rate=0.2554` `provider_weight=0.2107`	-

Roger Hinojo D 78 0 0.01 0.01 113% 0 0.1 6.6 54.6 11 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9929, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.9929` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0464)	`blend_weight=0.0464` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8664` `prior_reliability=0.2` `competition=La Liga`	wonTackle: 1.1399 -> 1.1674 totalShots: 0.324 -> 0.309 interceptionWon: 0.8387 -> 0.8266 fouls: 0.9735 -> 0.9685 wasFouled: 0.3961 -> 0.3911
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Pablo Ramón, Julen Agirrezabala', 'matchup_zone': 'LWB vs RW + RB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_assists: 0.033 -> 0.0435
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 18 by projected rating, fifa_overall 68.0)	`match_squad_rank=18` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.011` `goal_rate=0.0` `scorer_weight=0.0095`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0426` `assist_rate=0.0` `provider_weight=0.0348`	-

Leandro Cabrera D 90 0 0.07 0.06 ok 1 1.0 6.8 61.8 29 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9979, quality 0.437)	`market_value_eur=930000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yassir Zabiri', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_goals: 0.0556 -> 0.0732 expected_assists: 0.0296 -> 0.039
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 76.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0706` `goal_rate=0.0072` `scorer_weight=0.0586`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0382` `assist_rate=0.0` `provider_weight=0.0312`	-

Vanja Drkušić D 83 0 0.00 - n/a 0 0.0 6.7 18.8 11 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9939, quality 0.468)	`market_value_eur=5500000` `quality_factor=0.4683` `boost_factor=0.9939` `reference_quality=0.505` `history_matches=4` `history_shrink=0.5556`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0313)	`blend_weight=0.0313` `history_matches=4` `season_overlap_discount=1.0` `per90_to_match_factor=0.9219` `prior_reliability=0.0867` `competition=La Liga`	fouls: 0.6423 -> 0.6888 wasFouled: 0.6761 -> 0.7215 interceptionWon: 0.6788 -> 0.6575 wonTackle: 0.8876 -> 0.9042 totalShots: 0.3653 -> 0.3539
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yassir Zabiri', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 80.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0024` `assist_rate=0.0` `provider_weight=0.0023`	-

Clemens Riedel D 86 0 0.01 0.00 396% 0 0.1 6.7 42.8 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9974, quality 0.449)	`market_value_eur=3900000` `quality_factor=0.4486` `boost_factor=0.9974` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0112)	`blend_weight=0.0112` `history_matches=28` `season_overlap_discount=1.0` `per90_to_match_factor=0.9577` `prior_reliability=0.1133` `competition=La Liga`	fouls: 1.4847 -> 1.5058 interceptionWon: 0.908 -> 0.8979 wonTackle: 0.6238 -> 0.6294
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Iñigo Vicente', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 70.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0059` `goal_rate=0.0` `scorer_weight=0.0054`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0111` `assist_rate=0.0069` `provider_weight=0.0109`	-

Omar El Hilali D 88 0 0.00 - n/a 0 0.0 6.8 60.8 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0026, quality 0.589)	`market_value_eur=15900000` `quality_factor=0.5889` `boost_factor=1.0026` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0133)	`blend_weight=0.0133` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.983` `prior_reliability=0.2` `competition=La Liga`	totalCross: 2.5741 -> 2.5878 wasFouled: 0.8407 -> 0.8295 wonTackle: 1.1883 -> 1.1812
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Jorge Salinas, Julen Agirrezabala', 'matchup_zone': 'RWB vs LW + LB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_assists: 0.0952 -> 0.1254
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 75.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1179` `assist_rate=0.0915` `provider_weight=0.1222`	-

Ángel Fortuño G 90 0 0.00 - n/a 0.0 6.9 7.0 32 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9873, quality 0.437)	`market_value_eur=290000` `quality_factor=0.4374` `boost_factor=0.9873` `reference_quality=0.505` `history_matches=3` `history_shrink=0.625`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yassir Zabiri, Andrés Martín', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.3032}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	shots_faced: 12.4 -> 12.5 expected_saves: 3.04 -> 3.06 high_pressure_saves: 1.04 -> 1.05
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 89.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.4744`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.8905`	-

Pol Lozano M 78 0 0.12 0.03 341% 1 0.5 6.7 48.4 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9988, quality 0.472)	`market_value_eur=5800000` `quality_factor=0.472` `boost_factor=0.9988` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0020)	`blend_weight=0.002` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.8632` `prior_reliability=0.0267` `competition=La Liga`	wonTackle: 1.1313 -> 1.1377
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Iván Martín', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.46, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0149, 'skill_edge': 0.0181, 'height_edge': -0.008, 'attacker_skill': 0.4799, 'defender_skill': 0.4396, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Iván Martín', 'market_value': 2700000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4396}], 'xg_override': 0.09}	aerialWon: 0.3888 -> 0.9 totalShots: 0.9862 -> 1.0009 shotOffTarget: 0.6455 -> 0.6551 onTargetScoringAttempt: 0.3375 -> 0.3425
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_goals: 0.09 -> 0.1185 expected_assists: 0.0592 -> 0.078
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 75.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1117` `goal_rate=0.0764` `scorer_weight=0.107`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.075` `assist_rate=0.0571` `provider_weight=0.0765`	-

Bryan Zaragoza F 77 0 0.17 0.12 40% 1 1.1 7.0 58.3 15 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9994, quality 0.493)	`market_value_eur=7500000` `quality_factor=0.4927` `boost_factor=0.9994` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Jeanuël Belocian, Alvaro Mantilla', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8937, 'skill_edge': -0.0123, 'height_edge': -0.06, 'attacker_skill': 0.4927, 'defender_skill': 0.52, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Jeanuël Belocian', 'market_value': 12900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6027}, {'player': 'Alvaro Mantilla', 'market_value': 1200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.1274}	totalShots: 1.6634 -> 1.4866 shotOffTarget: 1.1176 -> 0.9988 onTargetScoringAttempt: 0.5457 -> 0.4877 expectedGoalsOnTarget: 0.1941 -> 0.1735 goals: 0.1546 -> 0.1382 expectedGoals: 0.1426 -> 0.1274
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_goals: 0.1274 -> 0.1678 expected_assists: 0.1447 -> 0.1906
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 77.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1545` `goal_rate=0.1382` `scorer_weight=0.178`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1735` `assist_rate=0.0442` `provider_weight=0.1525`	-

Roberto Fernández F 83 1 0.58 0.28 110% 2 1.5 6.8 62.9 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0039, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0039` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0121)	`blend_weight=0.0121` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=0.9256` `prior_reliability=0.1933` `competition=La Liga`	totalOffside: 0.9933 -> 0.9813 fouls: 1.5359 -> 1.5289 goals: 0.4238 -> 0.4302
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Jeanuël Belocian, Alvaro Mantilla', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.262, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0916, 'skill_edge': 0.0543, 'height_edge': 0.008, 'attacker_skill': 0.6408, 'defender_skill': 0.52, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Jeanuël Belocian', 'market_value': 12900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6027}, {'player': 'Alvaro Mantilla', 'market_value': 1200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.4418}	totalShots: 2.2815 -> 2.4905 shotOffTarget: 1.231 -> 1.3438 onTargetScoringAttempt: 1.0505 -> 1.1467 bigChanceMissed: 0.6125 -> 0.6686 goals: 0.4302 -> 0.4696 expectedGoalsOnTarget: 0.4095 -> 0.447 expectedGoals: 0.4047 -> 0.4418
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1085, xG scale 1.3171, xA scale 1.3171, team xA 0.96 = 0.66 x lambda)	`scoreline_reset=true` `team_lambda=1.46` `squad_xg_sum=1.1085` `squad_xa_sum=0.7277` `team_expected_assists=0.9585` `team_xa_to_xg_ratio=0.6565`	expected_goals: 0.4418 -> 0.5819 expected_assists: 0.0389 -> 0.0512
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 74.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.4412` `goal_rate=0.4696` `scorer_weight=0.6148`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0499` `assist_rate=0.0258` `provider_weight=0.0437`	-

Team totals 1 1.46 10 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Marko Dmitrović	G	4.4m	13.1%	Market-value substitute prior
Quilindschy Hartman	D	14.2m	32.5%	Market-value substitute prior
Unai Núñez	D	13.6m	21.7%	Market-value substitute prior
Urko González	M	22.4m	31.5%	Market-value substitute prior
Gabriel Moscardo	M	34.7m	69.6%	Market-value substitute prior
Tyrhys Dolan	F	25.7m	34.2%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Matteo Prati vs Javier Hernández will be the pivotal duel. Total antagonist xG — Home: 0.83, Away: 1.02. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.4% / 50.6%, dominance ratio 0.47, key duel: Matteo Prati vs Javier Hernández

Yassir Zabiri xG 0.41Iñigo Vicente xG 0.08Sergio Canales xG 0.10Roberto Fernández xG 0.44Bryan Zaragoza xG 0.13Javier Hernández xG 0.15

Summary

Antagonist matchup analysis for Racing Club vs Espanyol. Most likely scoreline: 1-1. Lambdas derived from 4 home and 7 away individual player duels. Head-to-head: Racing Club 5W-1D-4L vs Espanyol over 10 meetings.

Tactical parity between 4-2-3-1 and 5-4-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Matteo Prati vs Javier Hernández will be the pivotal duel. Total antagonist xG — Home: 0.83, Away: 1.02. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Arsenal vs Everton

Premier League · 20261024 · 4-2-3-1 vs 4-2-3-1

Predicted 1-0Winner: ArsenalWinning H 1-0 (10.4%)Winning A 0-1 (5.7%)Confidence 0.76λ home/away 1.85 / 1.02Most-likely P 10.4%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Arsenal vs Everton. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 1.712, Away 1.134). Final calibrated Poisson lambdas: Home 1.854, Away 1.016 (most likely score 1-0).

Home Starters 11/11 XGBoost (11 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.71 / 1.13 Final λ (H/A) 1.85 / 1.02

FBref Team Priors: Arsenal (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 2.069) vs Everton (Gls/90: 1.5, GA/90: 1.5 → E[λ]: 2.069) | Blend Weight: 0.192

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Arsenal	Everton
League position	2.00	8.00
Points per game	2.01	1.40
Attack index	1.09	0.88
Defense (concede) index	0.84	0.86
Form multiplier	1.03	0.97
Standing λ multiplier	0.97	0.89

Lambda decomposition (how the goal rates were built)

Stage	Arsenal λ	Everton λ
FBref Squad Prior E[λ] (weight 0.192)	2.069	2.069
Pre-mismatch	1.785	1.085
Pre-competitive-floor	1.937	1.062
Pre-calibration (Micro-duels)	1.712	1.134
Final λ	1.854	1.016

Scoreline distribution & markets

Top 5 scorelines	P
1-1	10.7%
1-0	10.4%
2-1	9.9%
2-0	9.7%
3-1	6.1%

Home win	56.9%
Draw	22.7%
Away win	20.4%
Over 2.5	54.7%
BTTS yes	53.9%

Pregame fair line — favorite Arsenal (56.9%), fair total 2.87, fair spread 0.84

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Arsenal — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Kai Havertz F 75 1 0.53 0.23 131% 3 1.3 6.8 50.7 24 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0214, quality 0.848)	`market_value_eur=58000000` `quality_factor=0.8478` `boost_factor=1.0214` `reference_quality=0.505` `history_matches=19` `history_shrink=0.2083`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0181)	`blend_weight=0.0181` `history_matches=19` `season_overlap_discount=1.0` `per90_to_match_factor=0.8356` `prior_reliability=0.1333` `competition=Premier League`	totalOffside: 0.9991 -> 1.0339 totalShots: 2.3967 -> 2.3685 wasFouled: 0.8931 -> 0.9071 totalCross: 0.7537 -> 0.7401
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Vitaliy Mykolenko, Jarrad Branthwaite', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.242, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 1.0622, 'skill_edge': 0.0203, 'height_edge': 0.022, 'attacker_skill': 0.8478, 'defender_skill': 0.8027, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Vitaliy Mykolenko', 'market_value': 26000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7498}, {'player': 'Jarrad Branthwaite', 'market_value': 46000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8555}], 'xg_override': 0.4071}	totalShots: 2.3961 -> 2.5452 shotOffTarget: 1.5301 -> 1.6253 onTargetScoringAttempt: 0.866 -> 0.9199 bigChanceMissed: 0.591 -> 0.6278 expectedGoals: 0.3833 -> 0.4071 expectedGoalsOnTarget: 0.3577 -> 0.3799 goals: 0.3443 -> 0.3657
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.4071 -> 0.5261 expected_assists: 0.0477 -> 0.0616
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 81.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.4091` `goal_rate=0.3657` `scorer_weight=0.4784`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0597` `assist_rate=0.0695` `provider_weight=0.0753`	-

Noni Madueke F 71 0 0.16 0.04 263% 2 0.8 6.9 41.3 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0134, quality 0.817)	`market_value_eur=48000000` `quality_factor=0.8168` `boost_factor=1.0134` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0019)	`blend_weight=0.0019` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.7883` `prior_reliability=0.02` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Vitaliy Mykolenko, Jarrad Branthwaite', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.184, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.977, 'skill_edge': 0.0064, 'height_edge': -0.022, 'attacker_skill': 0.8168, 'defender_skill': 0.8027, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Vitaliy Mykolenko', 'market_value': 26000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7498}, {'player': 'Jarrad Branthwaite', 'market_value': 46000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8555}], 'xg_override': 0.12}	totalShots: 1.9812 -> 1.9356 shotOffTarget: 1.4466 -> 1.4133 onTargetScoringAttempt: 0.5346 -> 0.5223 goals: 0.2156 -> 0.2106
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.12 -> 0.1551 expected_assists: 0.1334 -> 0.1724
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 80.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1437` `goal_rate=0.2106` `scorer_weight=0.1939`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1584` `assist_rate=0.0375` `provider_weight=0.1379`	-

Martin Ødegaard M 81 0 0.26 0.10 173% 2 0.6 7.3 52.9 24 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0160, quality 0.888)	`market_value_eur=88000000` `quality_factor=0.8879` `boost_factor=1.016` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0096)	`blend_weight=0.0096` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=0.9036` `prior_reliability=0.1067` `competition=Premier League`	wonTackle: 0.4598 -> 0.4717 totalShots: 1.3413 -> 1.35 fouls: 0.556 -> 0.5506
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ainsley Maitland-Niles', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.616, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2001, 'skill_edge': 0.1361, 'height_edge': 0.0, 'attacker_skill': 0.8879, 'defender_skill': 0.5854, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ainsley Maitland-Niles', 'market_value': 10900000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.5854}], 'xg_override': 0.2028}	aerialWon: 0.0593 -> 1.0 totalShots: 1.35 -> 1.6201 shotOffTarget: 0.815 -> 0.9781 onTargetScoringAttempt: 0.5265 -> 0.6319 expectedGoals: 0.169 -> 0.2028 goals: 0.1618 -> 0.1942 bigChanceMissed: 0.1431 -> 0.1717 expectedGoalsOnTarget: 0.1061 -> 0.1273
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.2028 -> 0.2621 expected_assists: 0.2046 -> 0.2645
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 86.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2306` `goal_rate=0.1942` `scorer_weight=0.2532`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.2324` `assist_rate=0.1876` `provider_weight=0.2468`	-

Eberechi Eze M 70 0 0.15 0.08 80% 1 1.1 6.8 50.3 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0123, quality 0.859)	`market_value_eur=63000000` `quality_factor=0.8589` `boost_factor=1.0123` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0035)	`blend_weight=0.0035` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.7766` `prior_reliability=0.0467` `competition=Premier League`	wasFouled: 1.8715 -> 1.8766
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Merlin Röhl', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.471, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0751, 'skill_edge': 0.1031, 'height_edge': -0.052, 'attacker_skill': 0.876, 'defender_skill': 0.6469, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Merlin Röhl', 'market_value': 18400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.6469}], 'xg_override': 0.1162}	aerialWon: 0.4691 -> 1.0 totalShots: 1.3238 -> 1.4232 shotOffTarget: 0.8916 -> 0.9586 onTargetScoringAttempt: 0.4312 -> 0.4636 expectedGoalsOnTarget: 0.2805 -> 0.3016 expectedGoals: 0.1081 -> 0.1162 goals: 0.1075 -> 0.1156
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.1162 -> 0.1502 expected_assists: 0.0533 -> 0.0689
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 84.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1395` `goal_rate=0.1156` `scorer_weight=0.1497`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0666` `assist_rate=0.0697` `provider_weight=0.0798`	-

Myles Lewis-Skelly D 75 0 0.03 0.01 175% 1 0.3 6.8 33.5 35 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0182, quality 0.869)	`market_value_eur=69000000` `quality_factor=0.8692` `boost_factor=1.0182` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0130)	`blend_weight=0.013` `history_matches=25` `season_overlap_discount=1.0` `per90_to_match_factor=0.8307` `prior_reliability=0.12` `competition=Premier League`	fouls: 1.5076 -> 1.494 wonTackle: 0.6257 -> 0.6176 totalShots: 0.5526 -> 0.5576
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kiernan Dewsbury-Hall', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.0259 -> 0.0335 expected_assists: 0.1022 -> 0.1321
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 78.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0329` `goal_rate=0.0` `scorer_weight=0.0268`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1237` `assist_rate=0.0` `provider_weight=0.1057`	-

Declan Rice M 86 0 0.09 0.04 106% 1 0.6 7.3 60.2 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0122, quality 0.897)	`market_value_eur=114000000` `quality_factor=0.8967` `boost_factor=1.0122` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0077)	`blend_weight=0.0077` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9607` `prior_reliability=0.1133` `competition=Premier League`	totalCross: 3.6522 -> 3.6589
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Merlin Röhl', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.521, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.149, 'skill_edge': 0.1133, 'height_edge': -0.012, 'attacker_skill': 0.8988, 'defender_skill': 0.6469, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Merlin Röhl', 'market_value': 18400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.6469}], 'xg_override': 0.0684}	totalShots: 0.7637 -> 0.8775 shotOffTarget: 0.565 -> 0.6492 aerialWon: 1.1627 -> 1.2 onTargetScoringAttempt: 0.1943 -> 0.2233 goals: 0.0856 -> 0.0984 expectedGoals: 0.0595 -> 0.0684
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.0684 -> 0.0884 expected_assists: 0.1927 -> 0.2491
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 88.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0846` `goal_rate=0.0984` `scorer_weight=0.1105`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.2205` `assist_rate=0.2106` `provider_weight=0.2675`	-

Riccardo Calafiori D 81 0 0.20 0.09 131% 1 0.8 6.8 45.7 24 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0140, quality 0.859)	`market_value_eur=63000000` `quality_factor=0.8589` `boost_factor=1.014` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0108)	`blend_weight=0.0108` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.8983` `prior_reliability=0.1267` `competition=Premier League`	goalAssist: 0.1298 -> 0.1386 wonTackle: 0.9445 -> 0.9394
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Thierno Barry', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.1551 -> 0.2005 expected_assists: 0.1133 -> 0.1464
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 82.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1817` `goal_rate=0.1307` `scorer_weight=0.1766`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1362` `assist_rate=0.1386` `provider_weight=0.1691`	-

Gabriel Magalhães D 90 0 0.19 0.08 122% 1 0.8 7.0 60.3 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0125, quality 0.871)	`market_value_eur=70000000` `quality_factor=0.8707` `boost_factor=1.0125` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0098)	`blend_weight=0.0098` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9997` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.7934 -> 0.7856 fouls: 0.7862 -> 0.7932
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Thierno Barry', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.1448 -> 0.1871 expected_assists: 0.0395 -> 0.0511
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 88.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1706` `goal_rate=0.0067` `scorer_weight=0.1497`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0498` `assist_rate=0.0258` `provider_weight=0.0433`	-

Ezri Konsa D 90 0 0.06 0.04 39% 0 0.3 6.8 53.2 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0110, quality 0.834)	`market_value_eur=53000000` `quality_factor=0.834` `boost_factor=1.011` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0005)	`blend_weight=0.0005` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9999` `prior_reliability=0.0067` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Thierno Barry', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.0434 -> 0.0561
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 84.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0546` `goal_rate=0.0` `scorer_weight=0.0449`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.012` `assist_rate=0.0` `provider_weight=0.0102`	-

Ben White D 73 0 0.03 0.01 204% 0 0.1 6.8 36.0 25 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0148, quality 0.732)	`market_value_eur=32000000` `quality_factor=0.732` `boost_factor=1.0148` `reference_quality=0.505` `history_matches=18` `history_shrink=0.2174`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0188)	`blend_weight=0.0188` `history_matches=18` `season_overlap_discount=1.0` `per90_to_match_factor=0.8063` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 1.6929 -> 1.7066 wasFouled: 0.9031 -> 0.8937
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Jack Grealish', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	expected_goals: 0.0246 -> 0.0318 expected_assists: 0.07 -> 0.0905
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 86.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0313` `goal_rate=0.0` `scorer_weight=0.0254`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0865` `assist_rate=0.2391` `provider_weight=0.1131`	-

David Raya G 90 0 0.00 - n/a 0.0 7.0 57.9 30 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0072, quality 0.739)	`market_value_eur=33000000` `quality_factor=0.7389` `boost_factor=1.0072` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.9882 -> 2.9662 wasFouled: 0.8363 -> 0.8289
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Thierno Barry, Kiernan Dewsbury-Hall', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.134}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4345, xG scale 1.2924, xA scale 1.2924, team xA 1.35 = 0.73 x lambda)	`scoreline_reset=true` `team_lambda=1.854` `squad_xg_sum=1.4345` `squad_xa_sum=1.0469` `team_expected_assists=1.3531` `team_xa_to_xg_ratio=0.7298`	shots_faced: 10.8 -> 9.7 expected_saves: 2.65 -> 2.38 high_pressure_saves: 0.91 -> 0.81
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 88.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.7964`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=1.3507`	-

Team totals 1 1.85 13 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Illan Meslier	G	4.6m	11.9%	Market-value substitute prior
William Saliba	D	15.4m	38.0%	Market-value substitute prior
Jurriën Timber	D	15.3m	37.7%	Market-value substitute prior
Martín Zubimendi	M	18.9m	72.8%	Market-value substitute prior
Bruno Guimarães	M	21.7m	72.8%	Market-value substitute prior
Bukayo Saka	F	27.1m	37.1%	Market-value substitute prior

Everton — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Thierno Barry F 84 0 0.36 0.31 ok 2 1.5 6.9 56.3 31 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0076, quality 0.758)	`market_value_eur=36000000` `quality_factor=0.7581` `boost_factor=1.0076` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0069)	`blend_weight=0.0069` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9382` `prior_reliability=0.1067` `competition=Premier League`	fouls: 0.8802 -> 0.8741
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Gabriel Magalhães, Riccardo Calafiori', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9494, 'skill_edge': -0.0584, 'height_edge': 0.024, 'attacker_skill': 0.7581, 'defender_skill': 0.888, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Gabriel Magalhães', 'market_value': 70000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8907}, {'player': 'Riccardo Calafiori', 'market_value': 63000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8852}], 'xg_override': 0.3662}	totalShots: 2.4491 -> 2.3252 bigChanceMissed: 1.3705 -> 1.3012 shotOffTarget: 1.3038 -> 1.2378 onTargetScoringAttempt: 1.1453 -> 1.0873 expectedGoalsOnTarget: 0.4588 -> 0.4356 goals: 0.4559 -> 0.4328 expectedGoals: 0.3857 -> 0.3662
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.3662 -> 0.3553 expected_assists: 0.0306 -> 0.0249
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 76.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.299` `goal_rate=0.4328` `scorer_weight=0.4121`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0246` `assist_rate=0.0` `provider_weight=0.0199`	-

Jack Grealish F 86 0 0.07 0.01 448% 1 0.5 7.0 39.4 25 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0066, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0066` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0007)	`blend_weight=0.0007` `history_matches=26` `season_overlap_discount=1.0` `per90_to_match_factor=0.9558` `prior_reliability=0.0067` `competition=Premier League`	fouls: 0.7406 -> 0.7468
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Gabriel Magalhães, Riccardo Calafiori', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7836, 'skill_edge': -0.1112, 'height_edge': -0.036, 'attacker_skill': 0.6408, 'defender_skill': 0.888, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Gabriel Magalhães', 'market_value': 70000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8907}, {'player': 'Riccardo Calafiori', 'market_value': 63000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8852}], 'xg_override': 0.0735}	totalShots: 1.1843 -> 0.928 shotOffTarget: 0.7994 -> 0.6264 onTargetScoringAttempt: 0.3849 -> 0.3016 bigChanceMissed: 0.1377 -> 0.1079 goals: 0.1151 -> 0.0902 expectedGoals: 0.0938 -> 0.0735 expectedGoalsOnTarget: 0.0644 -> 0.0505
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.1761 -> 0.143
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 82.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0688` `goal_rate=0.0902` `scorer_weight=0.0809`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1332` `assist_rate=0.1648` `provider_weight=0.1358`	-

Kiernan Dewsbury-Hall M 89 0 0.17 0.15 ok 2 1.5 7.2 58.9 28 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0103, quality 0.800)	`market_value_eur=44000000` `quality_factor=0.8002` `boost_factor=1.0103` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0101)	`blend_weight=0.0101` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9879` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 3.601 -> 3.6095 wonTackle: 0.7884 -> 0.7954 wasFouled: 2.0119 -> 2.0066
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Myles Lewis-Skelly', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.438, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9388, 'skill_edge': -0.0417, 'height_edge': 0.0, 'attacker_skill': 0.8002, 'defender_skill': 0.8928, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Myles Lewis-Skelly', 'market_value': 69000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8928}], 'xg_override': 0.1743}	aerialWon: 0.3465 -> 1.0 totalShots: 2.1154 -> 1.9859 shotOffTarget: 1.3009 -> 1.2213 onTargetScoringAttempt: 0.8127 -> 0.763 bigChanceMissed: 0.2619 -> 0.2459 goals: 0.2377 -> 0.2232 expectedGoalsOnTarget: 0.2069 -> 0.1942 expectedGoals: 0.1857 -> 0.1743
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1743 -> 0.1691 expected_assists: 0.1759 -> 0.1429
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 81.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1556` `goal_rate=0.2232` `scorer_weight=0.206`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1332` `assist_rate=0.1308` `provider_weight=0.1144`	-

Merlin Röhl M 84 0 0.05 0.01 354% 1 0.2 6.8 31.1 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0066, quality 0.615)	`market_value_eur=18400000` `quality_factor=0.615` `boost_factor=1.0066` `reference_quality=0.505` `history_matches=20` `history_shrink=0.2`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0165)	`blend_weight=0.0165` `history_matches=20` `season_overlap_discount=1.0` `per90_to_match_factor=0.9317` `prior_reliability=0.1267` `competition=Premier League`	totalCross: 1.4174 -> 1.4344 fouls: 1.4086 -> 1.3935 wonTackle: 1.0995 -> 1.1137 totalShots: 0.7914 -> 0.7784 wasFouled: 1.0024 -> 0.994
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Eberechi Eze', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.369, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9249, 'skill_edge': -0.1031, 'height_edge': 0.052, 'attacker_skill': 0.6469, 'defender_skill': 0.876, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Eberechi Eze', 'market_value': 63000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.876}], 'xg_override': 0.0494}	aerialWon: 1.1384 -> 1.3 totalShots: 0.7873 -> 0.7282 shotOffTarget: 0.5452 -> 0.5043 onTargetScoringAttempt: 0.2421 -> 0.2239
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0586 -> 0.0476
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 74.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0468` `goal_rate=0.0597` `scorer_weight=0.0529`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0465` `assist_rate=0.0654` `provider_weight=0.0506`	-

Harrison Armstrong M 84 0 0.08 0.04 98% 1 0.4 6.8 41.4 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0132, quality 0.725)	`market_value_eur=31000000` `quality_factor=0.7249` `boost_factor=1.0132` `reference_quality=0.505` `history_matches=20` `history_shrink=0.2`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0165)	`blend_weight=0.0165` `history_matches=20` `season_overlap_discount=1.0` `per90_to_match_factor=0.9288` `prior_reliability=0.1267` `competition=Premier League`	interceptionWon: 0.4556 -> 0.4803 fouls: 1.1461 -> 1.1675 totalShots: 1.0055 -> 0.9889 wonTackle: 0.9462 -> 0.9548 goalAssist: 0.0878 -> 0.0944 onTargetScoringAttempt: 0.3776 -> 0.3714
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Eberechi Eze, Declan Rice', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9119, 'skill_edge': -0.068, 'height_edge': 0.008, 'attacker_skill': 0.7364, 'defender_skill': 0.8874, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Eberechi Eze', 'market_value': 63000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.876}, {'player': 'Declan Rice', 'market_value': 114000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8988}], 'xg_override': 0.0844}	aerialWon: 0.6285 -> 1.2 totalShots: 0.9993 -> 0.9113 shotOffTarget: 0.6279 -> 0.5726 onTargetScoringAttempt: 0.3714 -> 0.3387 bigChanceMissed: 0.1998 -> 0.1822 goals: 0.0944 -> 0.0861 expectedGoals: 0.0925 -> 0.0844
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0655 -> 0.0532
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 73.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0786` `goal_rate=0.0861` `scorer_weight=0.0829`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0518` `assist_rate=0.0944` `provider_weight=0.0665`	-

James Garner M 87 0 0.06 0.03 98% 1 0.6 7.2 60.4 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0099, quality 0.834)	`market_value_eur=53000000` `quality_factor=0.834` `boost_factor=1.0099` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0035)	`blend_weight=0.0035` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9673` `prior_reliability=0.0533` `competition=Premier League`	wonTackle: 1.5012 -> 1.5128 fouls: 0.9578 -> 0.9629
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Eberechi Eze', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.428, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.0114, 'skill_edge': -0.0083, 'height_edge': 0.016, 'attacker_skill': 0.8576, 'defender_skill': 0.876, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Eberechi Eze', 'market_value': 63000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.876}], 'xg_override': 0.0588}	aerialWon: 0.3956 -> 1.1 totalShots: 0.8486 -> 0.8583 shotOffTarget: 0.6239 -> 0.631
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.1187 -> 0.0964
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 82.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0555` `goal_rate=0.0547` `scorer_weight=0.0549`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0919` `assist_rate=0.1014` `provider_weight=0.0865`	-

Vitaliy Mykolenko D 90 0 0.01 0.01 ok 0 0.2 6.7 51.7 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0062, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0062` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0098)	`blend_weight=0.0098` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9994` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.3485 -> 1.3352 totalCross: 2.4151 -> 2.4061 interceptionWon: 1.0985 -> 1.0926
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kai Havertz', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0646 -> 0.0525
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 77.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0065` `goal_rate=0.0` `scorer_weight=0.0057`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0511` `assist_rate=0.0081` `provider_weight=0.042`	-

Jarrad Branthwaite D 90 0 0.04 0.03 42% 1 0.5 6.8 54.0 22 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0207, quality 0.809)	`market_value_eur=46000000` `quality_factor=0.8089` `boost_factor=1.0207` `reference_quality=0.505` `history_matches=17` `history_shrink=0.2273`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0197)	`blend_weight=0.0197` `history_matches=17` `season_overlap_discount=1.0` `per90_to_match_factor=0.9956` `prior_reliability=0.1333` `competition=Premier League`	wasFouled: 0.8179 -> 0.8018 totalCross: 0.3679 -> 0.3607 interceptionWon: 1.1565 -> 1.1631
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kai Havertz', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 79.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.039` `goal_rate=0.0368` `scorer_weight=0.038`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0079` `assist_rate=0.0` `provider_weight=0.0066`	-

James Tarkowski D 90 0 0.04 0.07 43% 1 0.7 7.0 60.3 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9988, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.9988` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.3154 -> 1.3303 wasFouled: 1.6147 -> 1.6225
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kai Havertz', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0411 -> 0.0334
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 80.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0363` `goal_rate=0.1296` `scorer_weight=0.0462`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0328` `assist_rate=0.1676` `provider_weight=0.0417`	-

Ainsley Maitland-Niles D 78 0 0.01 0.01 31% 0 0.3 6.6 38.5 11 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0042, quality 0.533)	`market_value_eur=10900000` `quality_factor=0.533` `boost_factor=1.0042` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Martin Ødegaard', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.1829 -> 0.1484
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 77.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0051` `goal_rate=0.0` `scorer_weight=0.0046`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1379` `assist_rate=0.2678` `provider_weight=0.1855`	-

Jordan Pickford G 90 0 0.00 - n/a 0.0 7.0 58.4 31 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0019, quality 0.567)	`market_value_eur=13900000` `quality_factor=0.5671` `boost_factor=1.0019` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0087)	`blend_weight=0.0087` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	wasFouled: 0.3273 -> 0.3375 saves: 2.9404 -> 2.9496
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kai Havertz, Martin Ødegaard', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.7125}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.02 (squad xG sum 1.0471, xG scale 0.9703, xA scale 0.8122, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.016` `squad_xg_sum=1.0471` `squad_xa_sum=1.0007` `team_expected_assists=0.8128` `team_xa_to_xg_ratio=0.8`	shots_faced: 16.3 -> 17.6 expected_saves: 3.99 -> 4.31 high_pressure_saves: 1.37 -> 1.48
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 85.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.1461`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.8126`	-

Team totals 0 1.02 13 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Mark Travers	G	4.4m	10.9%	Market-value substitute prior
Jake O'Brien	D	14.2m	32.7%	Market-value substitute prior
Nathan Patterson	D	13.9m	31.6%	Market-value substitute prior
Hayden Hackney	M	26.4m	52.5%	Market-value substitute prior
Carlos Alcaraz	M	11.8m	70.3%	Market-value substitute prior
Brennan Johnson	F	21.8m	74.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Declan Rice vs James Garner will be the pivotal duel. Total antagonist xG — Home: 0.91, Away: 0.81. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.7% / 49.3%, dominance ratio 0.53, key duel: Declan Rice vs James Garner

Martin Ødegaard xG 0.20Kai Havertz xG 0.41Noni Madueke xG 0.12Kiernan Dewsbury-Hall xG 0.17Harrison Armstrong xG 0.08Thierno Barry xG 0.37

Summary

Antagonist matchup analysis for Arsenal vs Everton. Most likely scoreline: 1-0. Lambdas derived from 5 home and 6 away individual player duels. Head-to-head: Arsenal 7W-2D-1L vs Everton over 10 meetings.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Declan Rice vs James Garner will be the pivotal duel. Total antagonist xG — Home: 0.91, Away: 0.81. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Coventry vs Fulham

Premier League · 20261024 · 4-2-3-1 vs 4-2-3-1

Predicted 1-1Winner: DrawWinning H 1-0 (9.8%)Winning A 0-1 (10.5%)Confidence 0.7λ home/away 1.20 / 1.30Most-likely P 12.9%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Coventry vs Fulham. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 1.162, Away 1.342). Final calibrated Poisson lambdas: Home 1.201, Away 1.297 (most likely score 1-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.16 / 1.34 Final λ (H/A) 1.20 / 1.30

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Coventry	Fulham
League position	17.00	18.00
Points per game	1.09	1.01
Attack index	0.90	0.84
Defense (concede) index	0.94	1.20
Form multiplier	1.00	0.99
Standing λ multiplier	0.94	1.00

Lambda decomposition (how the goal rates were built)

Stage	Coventry λ	Fulham λ
Pre-competitive-floor	1.201	1.297
Pre-calibration (Micro-duels)	1.162	1.342
Final λ	1.201	1.297

competition calibration scale 1.0competition observed total goals 0.0quality gap applied Truemismatch score pressure applied Falsecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
1-1	12.9%
0-1	10.5%
1-0	9.8%
0-0	8.3%
1-2	8.3%

Home win	34.1%
Draw	27.2%
Away win	38.7%
Over 2.5	45.6%
BTTS yes	50.9%

Pregame fair line — favorite Fulham (38.7%), fair total 2.50, fair spread -0.10

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Coventry — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Taiwo Awoniyi F 72 1 0.30 0.17 70% 2 0.7 6.7 36.8 27 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9994, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9994` `reference_quality=0.505` `history_matches=22` `history_shrink=0.1852`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0096)	`blend_weight=0.0096` `history_matches=22` `season_overlap_discount=1.0` `per90_to_match_factor=0.8046` `prior_reliability=0.08` `competition=Premier League`	totalOffside: 0.7141 -> 0.7201 onTargetScoringAttempt: 0.7081 -> 0.7138 totalShots: 2.0316 -> 2.0371
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Calvin Bassey, Timothy Castagne', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8857, 'skill_edge': -0.0697, 'height_edge': -0.008, 'attacker_skill': 0.4939, 'defender_skill': 0.6488, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Calvin Bassey', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Timothy Castagne', 'market_value': 7600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.524}], 'xg_override': 0.2662}	totalShots: 2.0373 -> 1.8044 shotOffTarget: 1.3235 -> 1.1722 onTargetScoringAttempt: 0.7138 -> 0.6322 expectedGoalsOnTarget: 0.3999 -> 0.3542 bigChanceMissed: 0.3785 -> 0.3352 expectedGoals: 0.3006 -> 0.2662 goals: 0.2711 -> 0.2401
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2662 -> 0.2958 expected_assists: 0.0436 -> 0.0521
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 74.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2561` `goal_rate=0.2401` `scorer_weight=0.2714`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0508` `assist_rate=0.0` `provider_weight=0.0417`	-

Ephron Mason-Clark F 65 0 0.20 0.03 633% 1 0.2 6.7 26.9 19 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0133, quality 0.603)	`market_value_eur=17200000` `quality_factor=0.6027` `boost_factor=1.0133` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0118)	`blend_weight=0.0118` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.7172` `prior_reliability=0.04` `competition=Premier League`	totalCross: 1.9996 -> 2.0607 wasFouled: 0.6853 -> 0.7055 totalShots: 1.4335 -> 1.4166 fouls: 1.1834 -> 1.1977 onTargetScoringAttempt: 0.4607 -> 0.4553
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Calvin Bassey, Timothy Castagne', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9283, 'skill_edge': -0.0208, 'height_edge': -0.028, 'attacker_skill': 0.6027, 'defender_skill': 0.6488, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Calvin Bassey', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Timothy Castagne', 'market_value': 7600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.524}], 'xg_override': 0.1769}	totalShots: 1.4281 -> 1.3258 shotOffTarget: 0.9728 -> 0.9031 onTargetScoringAttempt: 0.4553 -> 0.4227 expectedGoals: 0.1906 -> 0.1769 goals: 0.1487 -> 0.138
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1769 -> 0.1966 expected_assists: 0.0627 -> 0.0749
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 75.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1785` `goal_rate=0.138` `scorer_weight=0.1629`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0722` `assist_rate=0.0` `provider_weight=0.0599`	-

Jack Rudoni M 79 0 0.21 0.17 ok 2 0.9 6.9 47.7 15 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0170, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.017` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'David Affengruber', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.46, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.971, 'skill_edge': -0.0197, 'height_edge': 0.0, 'attacker_skill': 0.6408, 'defender_skill': 0.6846, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'David Affengruber', 'market_value': 18100000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.6846}], 'xg_override': 0.1918}	aerialWon: 1.1146 -> 1.2 totalShots: 1.751 -> 1.7002 shotOffTarget: 1.1036 -> 1.0716 onTargetScoringAttempt: 0.6473 -> 0.6285 expectedGoalsOnTarget: 0.4327 -> 0.4202 bigChanceMissed: 0.3665 -> 0.3559 goals: 0.2275 -> 0.2209 expectedGoals: 0.1975 -> 0.1918
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1918 -> 0.2131 expected_assists: 0.1483 -> 0.177
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 75.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1919` `goal_rate=0.2209` `scorer_weight=0.2387`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.1622` `assist_rate=0.1214` `provider_weight=0.153`	-

Brandon Thomas-Asante F 82 0 0.15 0.03 347% 2 0.6 6.7 42.9 14 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0113, quality 0.595)	`market_value_eur=16500000` `quality_factor=0.5953` `boost_factor=1.0113` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0199)	`blend_weight=0.0199` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9066` `prior_reliability=0.0733` `competition=Premier League`	totalShots: 1.7295 -> 1.6952 totalCross: 0.694 -> 0.7129 interceptionWon: 2.6488 -> 2.6617 wasFouled: 3.1159 -> 3.1031 goalAssist: 0.5872 -> 0.5755 onTargetScoringAttempt: 0.4917 -> 0.4819 fouls: 0.3173 -> 0.311 totalOffside: 0.3173 -> 0.311
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Calvin Bassey, Timothy Castagne', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9352, 'skill_edge': -0.0241, 'height_edge': -0.02, 'attacker_skill': 0.5953, 'defender_skill': 0.6488, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Calvin Bassey', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Timothy Castagne', 'market_value': 7600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.524}], 'xg_override': 0.1336}	totalShots: 1.7197 -> 1.6083 shotOffTarget: 1.2378 -> 1.1576 onTargetScoringAttempt: 0.4819 -> 0.4507 goals: 0.1804 -> 0.1687 expectedGoals: 0.1429 -> 0.1336
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	assists: 1.0 -> 0
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1336 -> 0.1484 expected_assists: 0.031 -> 0.037
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 73.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1379` `goal_rate=0.1687` `scorer_weight=0.1768`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0363` `assist_rate=0.5755` `provider_weight=0.0462`	-

Matt Grimes M 87 0 0.03 0.01 203% 0 0.3 6.8 39.8 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9950, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.995` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0361)	`blend_weight=0.0361` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9718` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 2.3455 -> 2.4362 fouls: 0.9812 -> 0.9458 wonTackle: 0.7664 -> 0.7387 interceptionWon: 0.493 -> 0.4752 wasFouled: 0.5942 -> 0.6078 onTargetScoringAttempt: 0.1396 -> 0.1346
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Sander Berge', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.249, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.749, 'skill_edge': -0.1107, 'height_edge': -0.06, 'attacker_skill': 0.4759, 'defender_skill': 0.7219, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Sander Berge', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}], 'xg_override': 0.0257}	totalShots: 0.5749 -> 0.4306 shotOffTarget: 0.4386 -> 0.3285 aerialWon: 0.9206 -> 1.0 onTargetScoringAttempt: 0.1346 -> 0.1008 goals: 0.052 -> 0.0389 expectedGoals: 0.0343 -> 0.0257
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0625 -> 0.0746
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 76.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0282` `goal_rate=0.0389` `scorer_weight=0.0336`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0719` `assist_rate=0.0636` `provider_weight=0.0753`	-

Caleb Yirenkyi M 76 0 0.04 0.00 1233% 1 0.1 6.7 37.8 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0193, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0193` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0271)	`blend_weight=0.0271` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.8434` `prior_reliability=0.1` `competition=Premier League`	interceptionWon: 1.0581 -> 1.0294 fouls: 2.2731 -> 2.2572 wonTackle: 0.4672 -> 0.4545 totalCross: 0.3674 -> 0.3727
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Sander Berge', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.356, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.9055, 'skill_edge': -0.0123, 'height_edge': -0.052, 'attacker_skill': 0.6946, 'defender_skill': 0.7219, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Sander Berge', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}], 'xg_override': 0.0344}	totalShots: 0.6114 -> 0.5536 shotOffTarget: 0.4683 -> 0.424 aerialWon: 1.082 -> 1.1 onTargetScoringAttempt: 0.14 -> 0.1268
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0385 -> 0.046
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 73.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0375` `goal_rate=0.0386` `scorer_weight=0.0401`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.045` `assist_rate=0.0532` `provider_weight=0.0536`	-

Jay DaSilva D 90 0 0.08 0.05 40% 0 0.3 6.6 45.3 15 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0045, quality 0.541)	`market_value_eur=11600000` `quality_factor=0.5411` `boost_factor=1.0045` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0361)	`blend_weight=0.0361` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.995` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 0.781 -> 0.7708 totalCross: 2.7522 -> 2.7426 onTargetScoringAttempt: 0.2587 -> 0.2673 fouls: 0.7021 -> 0.6947 goalAssist: 0.1885 -> 0.1817 goals: 0.1602 -> 0.1544
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gonzalo García', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0692 -> 0.0769 expected_assists: 0.0826 -> 0.0986
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 73.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.074` `goal_rate=0.1544` `scorer_weight=0.0961`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0939` `assist_rate=0.1817` `provider_weight=0.1232`	-

Ethan Pinnock D 88 0 0.02 0.00 303% 0 0.1 6.7 15.1 32 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9932, quality 0.437)	`market_value_eur=2800000` `quality_factor=0.4374` `boost_factor=0.9932` `reference_quality=0.505` `history_matches=10` `history_shrink=0.3333`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gonzalo García', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 75.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.019` `goal_rate=0.0` `scorer_weight=0.0154`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0188` `assist_rate=0.0` `provider_weight=0.0152`	-

Bobby Thomas D 89 0 0.09 0.05 89% 1 1.0 7.0 42.4 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0170, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.017` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0343)	`blend_weight=0.0343` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9899` `prior_reliability=0.1267` `competition=Premier League`	interceptionWon: 1.194 -> 1.153 wasFouled: 0.9388 -> 0.9781 fouls: 0.7937 -> 0.8201 totalCross: 0.0997 -> 0.1142 totalShots: 0.8295 -> 0.8194 wonTackle: 0.6963 -> 0.6903
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gonzalo García', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0793 -> 0.0881 expected_assists: 0.052 -> 0.0621
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 74.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0843` `goal_rate=0.0` `scorer_weight=0.0705`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0602` `assist_rate=0.0` `provider_weight=0.0497`	-

Milan van Ewijk D 90 0 0.00 - n/a 0 0.0 6.7 38.6 14 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0211, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0211` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0394)	`blend_weight=0.0394` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.3396 -> 1.3065 wasFouled: 0.8102 -> 0.7783 interceptionWon: 1.155 -> 1.1292 totalCross: 0.9911 -> 1.0111 totalShots: 0.3802 -> 0.3652 fouls: 0.7293 -> 0.74
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alex Iwobi', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0717 -> 0.0856
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 75.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.082` `assist_rate=0.0` `provider_weight=0.0685`	-

Carl Rushworth G 90 0 0.00 - n/a 0.0 6.6 37.2 12 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0170, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.017` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0361)	`blend_weight=0.0361` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 3.1502 -> 3.0906 wasFouled: 0.1379 -> 0.1329
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gonzalo García, Josh King', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.342}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 1.0809, xG scale 1.1111, xA scale 1.1940, team xA 0.78 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.201` `squad_xg_sum=1.0809` `squad_xa_sum=0.6538` `team_expected_assists=0.7807` `team_xa_to_xg_ratio=0.65`	shots_faced: 12.7 -> 12.3 expected_saves: 3.1 -> 3.01 high_pressure_saves: 1.07 -> 1.04
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 76.0)	`match_squad_rank=17` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.2197`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.7398`	-

Team totals 1 1.20 10 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Daniel Bentley	G	4.4m	10.9%	Market-value substitute prior
Aurèle Amenda	D	14.2m	22.9%	Market-value substitute prior
Liam Kitching	D	14.1m	32.5%	Market-value substitute prior
Victor Torp	M	23.9m	70.3%	Market-value substitute prior
Josh Eccles	M	22.3m	51.3%	Market-value substitute prior
Sidiki Cherif	F	26.1m	59.5%	Market-value substitute prior

Fulham — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Antonee Robinson D 86 0 0.06 0.04 67% 1 0.3 6.7 49.4 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0074, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0074` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0125)	`blend_weight=0.0125` `history_matches=28` `season_overlap_discount=1.0` `per90_to_match_factor=0.9607` `prior_reliability=0.1267` `competition=Premier League`	wonTackle: 1.5398 -> 1.5521 fouls: 0.8352 -> 0.8248 interceptionWon: 1.0843 -> 1.0771
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Taiwo Awoniyi', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 80.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0601` `goal_rate=0.0491` `scorer_weight=0.0532`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0547` `assist_rate=0.0` `provider_weight=0.045`	-

Calvin Bassey D 90 0 0.05 0.04 ok 1 0.4 7.1 52.5 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0073, quality 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.0073` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0103)	`blend_weight=0.0103` `history_matches=37` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	fouls: 1.2004 -> 1.1932 wonTackle: 1.0007 -> 0.9955
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Brandon Thomas-Asante', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 78.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.045` `goal_rate=0.0066` `scorer_weight=0.0368`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0164` `assist_rate=0.0` `provider_weight=0.0132`	-

David Affengruber D 89 0 0.04 0.03 48% 1 0.5 7.0 55.9 33 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0033, quality 0.612)	`market_value_eur=18100000` `quality_factor=0.612` `boost_factor=1.0033` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0135)	`blend_weight=0.0135` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.988` `prior_reliability=0.2` `competition=La Liga`	totalShots: 0.5543 -> 0.5691 fouls: 1.1488 -> 1.1377 wasFouled: 0.6829 -> 0.6915 interceptionWon: 1.1796 -> 1.1859
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Jack Rudoni', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 76.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0389` `goal_rate=0.0198` `scorer_weight=0.0318`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0319` `assist_rate=0.0181` `provider_weight=0.0262`	-

Timothy Castagne D 86 0 0.07 0.05 39% 1 0.4 6.8 49.1 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9996, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9996` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.9557` `prior_reliability=0.1133` `competition=Premier League`	fouls: 1.2111 -> 1.2255 wasFouled: 0.7704 -> 0.7837
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Brandon Thomas-Asante', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 75.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.07` `goal_rate=0.0` `scorer_weight=0.0581`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0785` `assist_rate=0.0719` `provider_weight=0.073`	-

Bernd Leno G 90 0 0.00 - n/a 0.0 7.0 57.8 32 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9989, quality 0.468)	`market_value_eur=5500000` `quality_factor=0.4683` `boost_factor=0.9989` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0087)	`blend_weight=0.0087` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Taiwo Awoniyi, Jack Rudoni', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.1616}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	shots_faced: 11.0 -> 11.4 expected_saves: 2.69 -> 2.79 high_pressure_saves: 0.93 -> 0.96
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 79.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3663`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.758`	-

Sander Berge M 84 0 0.08 0.04 109% 1 0.5 7.1 53.6 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0058, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0058` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0078)	`blend_weight=0.0078` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9333` `prior_reliability=0.1133` `competition=Premier League`	wonTackle: 0.8444 -> 0.8378
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Matt Grimes', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.591, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.251, 'skill_edge': 0.1107, 'height_edge': 0.06, 'attacker_skill': 0.7219, 'defender_skill': 0.4759, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Matt Grimes', 'market_value': 5200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4759}], 'xg_override': 0.0852}`	aerialWon: 0.9697 -> 1.4 totalShots: 0.8742 -> 1.0936 shotOffTarget: 0.5689 -> 0.7117 onTargetScoringAttempt: 0.3053 -> 0.3819 goals: 0.0775 -> 0.097 expectedGoalsOnTarget: 0.0736 -> 0.0921 expectedGoals: 0.0681 -> 0.0852 bigChanceMissed: 0.0637 -> 0.0797
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 79.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0774` `goal_rate=0.097` `scorer_weight=0.0876`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.07` `assist_rate=0.0879` `provider_weight=0.079`	-

Shea Charles M 85 0 0.05 0.01 268% 1 0.3 7.0 40.9 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0204, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0204` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9404` `prior_reliability=0.0333` `competition=Premier League`	totalShots: 0.5539 -> 0.5814 totalCross: 0.1988 -> 0.214 wonTackle: 0.8767 -> 0.8858 wasFouled: 0.782 -> 0.7749
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Matt Grimes', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.567, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2156, 'skill_edge': 0.1027, 'height_edge': 0.044, 'attacker_skill': 0.704, 'defender_skill': 0.4759, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Matt Grimes', 'market_value': 5200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4759}], 'xg_override': 0.0497}`	aerialWon: 1.1519 -> 1.3 totalShots: 0.5814 -> 0.7067 shotOffTarget: 0.4257 -> 0.5175 onTargetScoringAttempt: 0.127 -> 0.1544 goals: 0.0429 -> 0.0521 expectedGoals: 0.0409 -> 0.0497
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 73.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0459` `goal_rate=0.0521` `scorer_weight=0.0481`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0622` `assist_rate=0.058` `provider_weight=0.0588`	-

Oscar Bobb F 72 0 0.14 0.09 61% 2 0.6 6.9 48.2 38 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0081, quality 0.694)	`market_value_eur=27000000` `quality_factor=0.6941` `boost_factor=1.0081` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0093)	`blend_weight=0.0093` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.8046` `prior_reliability=0.1` `competition=Premier League`	totalShots: 1.4798 -> 1.4661 fouls: 0.217 -> 0.2249
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ethan Pinnock, Bobby Thomas', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.194, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.991, 'skill_edge': 0.0539, 'height_edge': -0.06, 'attacker_skill': 0.6941, 'defender_skill': 0.5744, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ethan Pinnock', 'market_value': 2800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4465}, {'player': 'Bobby Thomas', 'market_value': 21000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7022}], 'xg_override': 0.1524}	totalShots: 1.4749 -> 1.4617 shotOffTarget: 0.9472 -> 0.9387
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	expected_goals: 0.1524 -> 0.1441 expected_assists: 0.1192 -> 0.1127
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 76.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1342` `goal_rate=0.1927` `scorer_weight=0.1728`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1066` `assist_rate=0.01` `provider_weight=0.0902`	-

Josh King M 77 0 0.18 0.11 75% 2 0.9 7.0 49.8 29 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0096, quality 0.786)	`market_value_eur=41000000` `quality_factor=0.7859` `boost_factor=1.0096` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Matt Grimes, Caleb Yirenkyi', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.303, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0926, 'skill_edge': 0.095, 'height_edge': -0.032, 'attacker_skill': 0.7964, 'defender_skill': 0.5852, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Matt Grimes', 'market_value': 5200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4759}, {'player': 'Caleb Yirenkyi', 'market_value': 23000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.6946}], 'xg_override': 0.1949}	aerialWon: 0.1325 -> 0.8 totalShots: 2.0206 -> 2.2077 shotOffTarget: 1.1587 -> 1.266 onTargetScoringAttempt: 0.8619 -> 0.9417 bigChanceMissed: 0.3849 -> 0.4205 expectedGoalsOnTarget: 0.2268 -> 0.2478 goals: 0.2167 -> 0.2368 expectedGoals: 0.1784 -> 0.1949
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	expected_goals: 0.1949 -> 0.1843 expected_assists: 0.141 -> 0.1333
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 78.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1683` `goal_rate=0.2368` `scorer_weight=0.2158`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1248` `assist_rate=0.1028` `provider_weight=0.1066`	-

Gonzalo García F 82 1 0.34 0.24 42% 2 1.1 6.7 49.8 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0090, quality 0.758)	`market_value_eur=36000000` `quality_factor=0.7581` `boost_factor=1.009` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0103)	`blend_weight=0.0103` `history_matches=37` `season_overlap_discount=1.0` `per90_to_match_factor=0.9136` `prior_reliability=0.1333` `competition=Premier League`	fouls: 1.0137 -> 1.0221 totalShots: 2.093 -> 2.0997 wasFouled: 0.3708 -> 0.3764
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ethan Pinnock, Bobby Thomas', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.251, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0745, 'skill_edge': 0.0827, 'height_edge': -0.032, 'attacker_skill': 0.7581, 'defender_skill': 0.5744, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ethan Pinnock', 'market_value': 2800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4465}, {'player': 'Bobby Thomas', 'market_value': 21000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7022}], 'xg_override': 0.3547}	totalShots: 2.0997 -> 2.2561 shotOffTarget: 1.1943 -> 1.2833 onTargetScoringAttempt: 0.8941 -> 0.9607 bigChanceMissed: 0.8251 -> 0.8866 expectedGoals: 0.3301 -> 0.3547 goals: 0.3038 -> 0.3264 expectedGoalsOnTarget: 0.1851 -> 0.1989
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	expected_goals: 0.3547 -> 0.3354
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 78.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2849` `goal_rate=0.3264` `scorer_weight=0.312`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0662` `assist_rate=0.0` `provider_weight=0.0548`	-

Alex Iwobi M 83 0 0.15 0.06 136% 2 1.1 7.4 51.7 35 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0050, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.005` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0106)	`blend_weight=0.0106` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.924` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 4.3923 -> 4.3703 totalShots: 2.0182 -> 2.0018 interceptionWon: 0.3538 -> 0.3647 onTargetScoringAttempt: 0.67 -> 0.6629
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Milan van Ewijk', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.468, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.9828, 'skill_edge': -0.0437, 'height_edge': 0.032, 'attacker_skill': 0.6408, 'defender_skill': 0.7379, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Milan van Ewijk', 'market_value': 23000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.7379}], 'xg_override': 0.1571}	aerialWon: 0.0833 -> 1.1 totalShots: 2.0111 -> 1.9765 shotOffTarget: 1.3482 -> 1.325 onTargetScoringAttempt: 0.6629 -> 0.6515
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3718, xG scale 0.9454, xA scale 0.9454, team xA 0.89 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=1.297` `squad_xg_sum=1.3718` `squad_xa_sum=0.9435` `team_expected_assists=0.8921` `team_xa_to_xg_ratio=0.6878`	expected_goals: 0.1571 -> 0.1485 expected_assists: 0.2215 -> 0.2094
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 80.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.138` `goal_rate=0.211` `scorer_weight=0.1856`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.1889` `assist_rate=0.1322` `provider_weight=0.1675`	-

Team totals 1 1.30 16 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Benjamin Lecomte	G	4.4m	10.9%	Market-value substitute prior
Joachim Andersen	D	14.4m	23.3%	Market-value substitute prior
Ryan Sessegnon	D	18.0m	61.8%	Market-value substitute prior
Hugo Larsson	M	23.1m	54.9%	Market-value substitute prior
Emile Smith Rowe	M	18.4m	70.6%	Market-value substitute prior
Kevin	F	19.0m	73.9%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Caleb Yirenkyi vs Josh King will be the pivotal duel. Total antagonist xG — Home: 0.83, Away: 0.99. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 48.5% / 51.5%, dominance ratio 0.45, key duel: Caleb Yirenkyi vs Josh King

Jack Rudoni xG 0.19Brandon Thomas-Asante xG 0.13Taiwo Awoniyi xG 0.27Alex Iwobi xG 0.16Josh King xG 0.19Gonzalo García xG 0.35

Summary

Antagonist matchup analysis for Coventry vs Fulham. Most likely scoreline: 1-1. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Coventry 2W-0D-0L vs Fulham over 2 meetings.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Caleb Yirenkyi vs Josh King will be the pivotal duel. Total antagonist xG — Home: 0.83, Away: 0.99. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Aston Villa vs Man City

Premier League · 20261024 · 4-2-3-1 vs 4-2-3-1

Predicted 0-2Winner: Man CityWinning H 2-1 (3.1%)Winning A 0-2 (10.3%)Confidence 0.8λ home/away 0.89 / 2.62Most-likely P 10.3%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Aston Villa vs Man City. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 1.031, Away 2.271). Final calibrated Poisson lambdas: Home 0.890, Away 2.619 (most likely score 0-2).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.03 / 2.27 Final λ (H/A) 0.89 / 2.62

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Aston Villa	Man City
League position	12.00	1.00
Points per game	1.24	2.24
Attack index	0.94	1.25
Defense (concede) index	0.84	1.09
Form multiplier	0.95	1.05
Standing λ multiplier	0.90	1.14

Lambda decomposition (how the goal rates were built)

Stage	Aston Villa λ	Man City λ
Pre-mismatch	0.993	2.516
Pre-calibration (Micro-duels)	1.031	2.271
Final λ	0.890	2.619

Scoreline distribution & markets

Top 5 scorelines	P
0-2	10.3%
1-2	9.1%
0-3	9.0%
1-3	8.0%
0-1	7.8%

Home win	10.4%
Draw	15.3%
Away win	74.3%
Over 2.5	68.1%
BTTS yes	54.7%

Pregame fair line — favorite Man City (74.3%), fair total 3.51, fair spread -1.73

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Aston Villa — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Victor Lindelöf D 87 0 0.03 0.02 43% 0 0.1 6.8 35.8 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.460)	`market_value_eur=4800000` `quality_factor=0.4597` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=24` `history_shrink=0.1724`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0149)	`blend_weight=0.0149` `history_matches=24` `season_overlap_discount=1.0` `per90_to_match_factor=0.966` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 0.7915 -> 0.7797 wonTackle: 0.5485 -> 0.5403 totalShots: 0.366 -> 0.3605
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Iliman Ndiaye', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0497 -> 0.0341
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 77.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0335` `goal_rate=0.0` `scorer_weight=0.0273`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0127` `assist_rate=0.0099` `provider_weight=0.0115`	-

Matty Cash D 87 0 0.02 0.03 ok 0 0.6 6.7 55.3 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0040, quality 0.629)	`market_value_eur=19800000` `quality_factor=0.6291` `boost_factor=1.004` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.9653` `prior_reliability=0.1267` `competition=Premier League`	totalCross: 2.4923 -> 2.47 wonTackle: 1.2279 -> 1.2396 wasFouled: 1.0426 -> 1.0515
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Erling Haaland', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0328 -> 0.0225 expected_assists: 0.0384 -> 0.0294
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 81.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0222` `goal_rate=0.0054` `scorer_weight=0.018`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.029` `assist_rate=0.0563` `provider_weight=0.0354`	-

Zion Suzuki G 90 0 0.00 - n/a 0.0 7.0 34.6 12 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0300, quality 0.725)	`market_value_eur=31000000` `quality_factor=0.7249` `boost_factor=1.03` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0197)	`blend_weight=0.0197` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.0667` `competition=Premier League`	saves: 2.9816 -> 2.9425 wasFouled: 0.7407 -> 0.7261
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Erling Haaland, Phil Foden', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 2.271}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	shots_faced: 21.6 -> 24.9 expected_saves: 5.29 -> 6.1 high_pressure_saves: 1.82 -> 2.1
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 76.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=0.9371`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.5267`	-

Tyrone Mings D 89 0 0.04 0.05 ok 1 0.4 6.8 39.3 27 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9965, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.9965` `reference_quality=0.505` `history_matches=23` `history_shrink=0.1786`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0015)	`blend_weight=0.0015` `history_matches=23` `season_overlap_discount=1.0` `per90_to_match_factor=0.9889` `prior_reliability=0.0133` `competition=Premier League`	wonTackle: 0.5724 -> 0.5791
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Erling Haaland', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0565 -> 0.0388
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 77.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0381` `goal_rate=0.0` `scorer_weight=0.031`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0128` `assist_rate=0.0` `provider_weight=0.0103`	-

Ian Maatsen D 83 0 0.04 0.04 ok 1 0.6 6.7 48.9 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0090, quality 0.739)	`market_value_eur=33000000` `quality_factor=0.7389` `boost_factor=1.009` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0106)	`blend_weight=0.0106` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.9273` `prior_reliability=0.1267` `competition=Premier League`	totalCross: 2.0573 -> 2.0407 fouls: 0.9954 -> 1.0107 wonTackle: 1.3705 -> 1.3612 totalShots: 0.6853 -> 0.6935 interceptionWon: 1.227 -> 1.2347
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Phil Foden', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0536 -> 0.0368 expected_assists: 0.1208 -> 0.0924
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 79.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0361` `goal_rate=0.0` `scorer_weight=0.0294`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0883` `assist_rate=0.0496` `provider_weight=0.0739`	-

Boubacar Kamara M 88 0 0.03 0.01 171% 1 0.2 7.0 45.4 14 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0158, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0158` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0144)	`blend_weight=0.0144` `history_matches=25` `season_overlap_discount=1.0` `per90_to_match_factor=0.9738` `prior_reliability=0.1333` `competition=Premier League`	wasFouled: 2.3863 -> 2.3589 fouls: 1.6548 -> 1.6661 totalShots: 0.6447 -> 0.6354 wonTackle: 1.4994 -> 1.4918 interceptionWon: 0.8465 -> 0.8413 totalCross: 0.1376 -> 0.1426
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ayyoub Bouaddi', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.394, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9611, 'skill_edge': -0.0225, 'height_edge': -0.004, 'attacker_skill': 0.847, 'defender_skill': 0.8969, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Ayyoub Bouaddi', 'market_value': 98000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8969}], 'xg_override': 0.0447}	aerialWon: 1.5099 -> 1.1 totalShots: 0.6421 -> 0.6171 shotOffTarget: 0.4673 -> 0.4491 onTargetScoringAttempt: 0.1748 -> 0.168
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0447 -> 0.0307 expected_assists: 0.0454 -> 0.0347
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 84.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0302` `goal_rate=0.0437` `scorer_weight=0.0304`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0341` `assist_rate=0.0641` `provider_weight=0.0415`	-

João Gomes M 82 0 0.02 0.02 ok 0 0.4 6.8 53.0 27 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0086, quality 0.758)	`market_value_eur=36000000` `quality_factor=0.7581` `boost_factor=1.0086` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0020)	`blend_weight=0.002` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9066` `prior_reliability=0.0267` `competition=Premier League`	wonTackle: 1.9402 -> 1.9453
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ayyoub Bouaddi', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.337, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8781, 'skill_edge': -0.0469, 'height_edge': -0.036, 'attacker_skill': 0.7926, 'defender_skill': 0.8969, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Ayyoub Bouaddi', 'market_value': 98000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8969}], 'xg_override': 0.0324}	aerialWon: 0.6518 -> 0.9 totalShots: 0.5675 -> 0.4984 shotOffTarget: 0.3859 -> 0.3389 onTargetScoringAttempt: 0.1816 -> 0.1595 expectedGoalsOnTarget: 0.0479 -> 0.0421 goals: 0.0452 -> 0.0397
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0324 -> 0.0222 expected_assists: 0.0585 -> 0.0447
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 78.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.022` `goal_rate=0.0397` `scorer_weight=0.0242`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0437` `assist_rate=0.0794` `provider_weight=0.0533`	-

Nicolas Jackson F 80 0 0.26 0.15 77% 3 1.5 7.1 38.9 11 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0403, quality 0.800)	`market_value_eur=44000000` `quality_factor=0.8002` `boost_factor=1.0403` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0157)	`blend_weight=0.0157` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.8917` `prior_reliability=0.0533` `competition=Premier League`	totalShots: 2.7605 -> 2.717 onTargetScoringAttempt: 1.1641 -> 1.1458 totalCross: 0.423 -> 0.4339 wasFouled: 0.5247 -> 0.5164 totalOffside: 0.4928 -> 0.485 goals: 0.4875 -> 0.4798 fouls: 0.3349 -> 0.3296
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Joško Gvardiol, Rúben Dias', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9397, 'skill_edge': -0.037, 'height_edge': -0.004, 'attacker_skill': 0.8002, 'defender_skill': 0.8826, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Joško Gvardiol', 'market_value': 69000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.89}, {'player': 'Rúben Dias', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}], 'xg_override': 0.3779}	totalShots: 2.7421 -> 2.5768 shotOffTarget: 1.5963 -> 1.5 onTargetScoringAttempt: 1.1458 -> 1.0767 goals: 0.4798 -> 0.4509 bigChanceMissed: 0.4315 -> 0.4055 expectedGoals: 0.4021 -> 0.3779 expectedGoalsOnTarget: 0.3297 -> 0.3098
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3779 -> 0.2597 expected_assists: 0.1112 -> 0.085
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 79.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.2287` `goal_rate=0.4509` `scorer_weight=0.304`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0815` `assist_rate=0.0` `provider_weight=0.068`	-

Ibrahim Mbaye F 80 0 0.11 0.03 226% 2 0.5 6.9 27.3 10 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0342, quality 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.0342` `reference_quality=0.505` `history_matches=4` `history_shrink=0.5556`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Joško Gvardiol, Rúben Dias', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8153, 'skill_edge': -0.0777, 'height_edge': -0.048, 'attacker_skill': 0.71, 'defender_skill': 0.8826, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Joško Gvardiol', 'market_value': 69000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.89}, {'player': 'Rúben Dias', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}], 'xg_override': 0.1624}	totalShots: 1.705 -> 1.3901 onTargetScoringAttempt: 0.9265 -> 0.7554 shotOffTarget: 0.7784 -> 0.6346 bigChanceMissed: 0.3245 -> 0.2646 goals: 0.2362 -> 0.1926 expectedGoals: 0.1992 -> 0.1624 expectedGoalsOnTarget: 0.0852 -> 0.0695
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1624 -> 0.1115 expected_assists: 0.0807 -> 0.0617
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 76.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1055` `goal_rate=0.1926` `scorer_weight=0.1274`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0598` `assist_rate=0.0` `provider_weight=0.0494`	-

Emiliano Buendía F 76 0 0.10 0.11 ok 1 1.3 6.9 49.8 42 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0022, quality 0.575)	`market_value_eur=14600000` `quality_factor=0.5748` `boost_factor=1.0022` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Joško Gvardiol, Rúben Dias', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7082, 'skill_edge': -0.1385, 'height_edge': -0.06, 'attacker_skill': 0.5748, 'defender_skill': 0.8826, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Joško Gvardiol', 'market_value': 69000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.89}, {'player': 'Rúben Dias', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}], 'xg_override': 0.1423}	totalShots: 1.8899 -> 1.3385 shotOffTarget: 1.2554 -> 0.8891 onTargetScoringAttempt: 0.6345 -> 0.4494 bigChanceMissed: 0.2251 -> 0.1594 goals: 0.2081 -> 0.1474 expectedGoals: 0.2009 -> 0.1423 expectedGoalsOnTarget: 0.0753 -> 0.0533
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1423 -> 0.0977 expected_assists: 0.1032 -> 0.0789
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 80.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0931` `goal_rate=0.1474` `scorer_weight=0.1003`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0759` `assist_rate=0.0026` `provider_weight=0.0631`	-

Alysson F 68 0 0.10 0.01 1549% 1 0.1 6.7 31.5 19 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0093, quality 0.592)	`market_value_eur=16200000` `quality_factor=0.5921` `boost_factor=1.0093` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0046)	`blend_weight=0.0046` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.7592` `prior_reliability=0.02` `competition=Premier League`	wonTackle: 0.5844 -> 0.6052 totalShots: 1.3581 -> 1.3518
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Joško Gvardiol, Rúben Dias', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7902, 'skill_edge': -0.1307, 'height_edge': -0.012, 'attacker_skill': 0.5921, 'defender_skill': 0.8826, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Joško Gvardiol', 'market_value': 69000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.89}, {'player': 'Rúben Dias', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}], 'xg_override': 0.1388}	totalShots: 1.356 -> 1.0715 shotOffTarget: 0.9052 -> 0.7153 onTargetScoringAttempt: 0.4508 -> 0.3562 expectedGoals: 0.1757 -> 0.1388 goals: 0.1395 -> 0.1102 expectedGoalsOnTarget: 0.0285 -> 0.0225
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.89 (squad xG sum 1.2961, xG scale 0.6867, xA scale 0.7646, team xA 0.58 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.89` `squad_xg_sum=1.2961` `squad_xa_sum=0.7566` `team_expected_assists=0.5785` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1388 -> 0.0953 expected_assists: 0.0591 -> 0.0452
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 70.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0909` `goal_rate=0.1102` `scorer_weight=0.0809`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0442` `assist_rate=0.0` `provider_weight=0.0362`	-

Team totals 0 0.89 14 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Marco Bizot	G	4.4m	13.1%	Market-value substitute prior
Matteo Ruggeri	D	11.5m	62.3%	Market-value substitute prior
Taylor Harwood-Bellis	D	14.6m	34.5%	Market-value substitute prior
Johan Manzambi	M	23.7m	57.7%	Market-value substitute prior
Amadou Onana	M	23.4m	56.1%	Market-value substitute prior
Alejandro Garnacho	F	16.8m	73.9%	Market-value substitute prior

Man City — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Erling Haaland F 88 2 0.99 0.50 98% 4 2.8 7.7 57.6 30 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0126, quality 0.900)	`market_value_eur=240000000` `quality_factor=0.9` `boost_factor=1.0126` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9746` `prior_reliability=0.1333` `competition=Premier League`	totalShots: 3.1105 -> 3.1267 onTargetScoringAttempt: 1.3899 -> 1.3995 fouls: 0.9053 -> 0.897
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Matty Cash, Tyrone Mings', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.368, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.2469, 'skill_edge': 0.148, 'height_edge': 0.02, 'attacker_skill': 0.9, 'defender_skill': 0.5712, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Matty Cash', 'market_value': 19800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6892}, {'player': 'Tyrone Mings', 'market_value': 3200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4531}], 'xg_override': 0.6708}	totalShots: 3.1267 -> 3.8987 shotOffTarget: 1.7206 -> 2.1454 onTargetScoringAttempt: 1.3995 -> 1.745 goals: 0.8726 -> 1.088 expectedGoalsOnTarget: 0.8287 -> 1.0333 bigChanceMissed: 0.7667 -> 0.956 expectedGoals: 0.538 -> 0.6708
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	goals: 1.0 -> 0
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.6708 -> 0.9851 expected_assists: 0.0667 -> 0.098
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 91.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=2` `goal_probability=0.6266` `goal_rate=1.088` `scorer_weight=1.2314`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0934` `assist_rate=0.0792` `provider_weight=0.1085`	-

Jérémy Doku F 82 0 0.29 0.06 399% 3 1.0 7.4 46.3 29 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0144, quality 0.871)	`market_value_eur=70000000` `quality_factor=0.8707` `boost_factor=1.0144` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Matty Cash, Tyrone Mings', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.275, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1099, 'skill_edge': 0.1348, 'height_edge': -0.06, 'attacker_skill': 0.8707, 'defender_skill': 0.5712, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Matty Cash', 'market_value': 19800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6892}, {'player': 'Tyrone Mings', 'market_value': 3200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4531}], 'xg_override': 0.1981}	totalShots: 2.5036 -> 2.7787 shotOffTarget: 1.5456 -> 1.7155 onTargetScoringAttempt: 0.9579 -> 1.0632 expectedGoalsOnTarget: 0.3733 -> 0.4143 goals: 0.3209 -> 0.3562 expectedGoals: 0.1785 -> 0.1981
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.1981 -> 0.2909 expected_assists: 0.2283 -> 0.3351
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 84.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2524` `goal_rate=0.3562` `scorer_weight=0.3636`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.2847` `assist_rate=0.3009` `provider_weight=0.4189`	-

Phil Foden M 74 0 0.31 0.13 137% 2 0.8 7.0 49.4 30 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0123, quality 0.857)	`market_value_eur=62000000` `quality_factor=0.8569` `boost_factor=1.0123` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0096)	`blend_weight=0.0096` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.8271` `prior_reliability=0.1267` `competition=Premier League`	totalCross: 3.7732 -> 3.7871 fouls: 0.5573 -> 0.5645 onTargetScoringAttempt: 0.6966 -> 0.6899 wasFouled: 1.048 -> 1.0546 goalAssist: 0.1941 -> 0.2006
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ian Maatsen', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.472, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9875, 'skill_edge': 0.0195, 'height_edge': -0.028, 'attacker_skill': 0.8569, 'defender_skill': 0.8135, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ian Maatsen', 'market_value': 33000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8135}], 'xg_override': 0.2078}	aerialWon: 0.5135 -> 0.8 totalShots: 1.7276 -> 1.706 shotOffTarget: 1.0267 -> 1.0139 onTargetScoringAttempt: 0.6899 -> 0.6813
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.2078 -> 0.3052 expected_assists: 0.1972 -> 0.2896
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 84.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.263` `goal_rate=0.2236` `scorer_weight=0.3239`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.2514` `assist_rate=0.2006` `provider_weight=0.2936`	-

Ayyoub Bouaddi M 87 0 0.06 0.00 2862% 1 0.1 7.0 25.1 11 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0646, quality 0.893)	`market_value_eur=98000000` `quality_factor=0.8926` `boost_factor=1.0646` `reference_quality=0.505` `history_matches=4` `history_shrink=0.5556`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0024)	`blend_weight=0.0024` `history_matches=4` `season_overlap_discount=1.0` `per90_to_match_factor=0.9703` `prior_reliability=0.0067` `competition=Premier League`	interceptionWon: 0.5392 -> 0.5614
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Boubacar Kamara', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.446, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.0389, 'skill_edge': 0.0225, 'height_edge': 0.004, 'attacker_skill': 0.8969, 'defender_skill': 0.847, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Boubacar Kamara', 'market_value': 49000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.847}], 'xg_override': 0.0429}	aerialWon: 0.3341 -> 1.2 totalShots: 0.6167 -> 0.6407 shotOffTarget: 0.4703 -> 0.4886 onTargetScoringAttempt: 0.1464 -> 0.1521
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.0429 -> 0.063 expected_assists: 0.0554 -> 0.0814
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 80.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0611` `goal_rate=0.0691` `scorer_weight=0.0788`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0782` `assist_rate=0.0545` `provider_weight=0.0807`	-

Enzo Fernández M 86 0 0.20 0.18 ok 2 1.5 7.2 59.6 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0125, quality 0.897)	`market_value_eur=116000000` `quality_factor=0.897` `boost_factor=1.0125` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0014)	`blend_weight=0.0014` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9531` `prior_reliability=0.02` `competition=Premier League`	totalCross: 3.76 -> 3.7548
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Boubacar Kamara', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.415, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9932, 'skill_edge': 0.0234, 'height_edge': -0.028, 'attacker_skill': 0.8989, 'defender_skill': 0.847, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Boubacar Kamara', 'market_value': 49000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.847}], 'xg_override': 0.1341}	aerialWon: 0.9077 -> 1.0 totalShots: 1.5575 -> 1.5469 shotOffTarget: 0.9709 -> 0.9643
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.1341 -> 0.1969 expected_assists: 0.192 -> 0.282
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 86.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1787` `goal_rate=0.1869` `scorer_weight=0.2461`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.2457` `assist_rate=0.1246` `provider_weight=0.2256`	-

Joško Gvardiol D 84 0 0.10 0.07 34% 1 0.5 6.8 46.0 17 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0182, quality 0.869)	`market_value_eur=69000000` `quality_factor=0.8692` `boost_factor=1.0182` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0130)	`blend_weight=0.013` `history_matches=25` `season_overlap_discount=1.0` `per90_to_match_factor=0.9321` `prior_reliability=0.12` `competition=Premier League`	wasFouled: 0.8217 -> 0.811 totalCross: 0.3339 -> 0.343 wonTackle: 0.9509 -> 0.9453
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Nicolas Jackson', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.065 -> 0.0955 expected_assists: 0.1279 -> 0.1878
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 85.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0911` `goal_rate=0.141` `scorer_weight=0.1194`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1712` `assist_rate=0.3181` `provider_weight=0.2347`	-

Marc Guéhi D 90 0 0.13 0.14 ok 1 0.8 7.2 62.0 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0117, quality 0.872)	`market_value_eur=71000000` `quality_factor=0.8721` `boost_factor=1.0117` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.63 -> 0.6426 interceptionWon: 0.8325 -> 0.8387
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alysson', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.09 -> 0.1322 expected_assists: 0.0587 -> 0.0862
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 85.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1238` `goal_rate=0.0818` `scorer_weight=0.1245`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0826` `assist_rate=0.1401` `provider_weight=0.1077`	-

Rúben Dias D 89 0 0.10 0.03 266% 1 0.3 7.1 44.4 24 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0132, quality 0.840)	`market_value_eur=55000000` `quality_factor=0.8399` `boost_factor=1.0132` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0114)	`blend_weight=0.0114` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.984` `prior_reliability=0.1333` `competition=Premier League`	fouls: 1.4058 -> 1.3898
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Nicolas Jackson', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.0683 -> 0.1003 expected_assists: 0.0747 -> 0.1097
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 87.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0954` `goal_rate=0.0157` `scorer_weight=0.0802`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1039` `assist_rate=0.0` `provider_weight=0.0878`	-

Abdukodir Khusanov D 88 0 0.04 0.02 89% 0 0.2 7.0 46.1 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0154, quality 0.813)	`market_value_eur=47000000` `quality_factor=0.8129` `boost_factor=1.0154` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0144)	`blend_weight=0.0144` `history_matches=25` `season_overlap_discount=1.0` `per90_to_match_factor=0.9829` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.9081 -> 0.9305 fouls: 0.8307 -> 0.8187 totalCross: 0.4608 -> 0.4683 totalShots: 0.4756 -> 0.4687
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Emiliano Buendía', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.0291 -> 0.0427 expected_assists: 0.0437 -> 0.0642
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 82.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0418` `goal_rate=0.0` `scorer_weight=0.0342`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0622` `assist_rate=0.0` `provider_weight=0.0514`	-

Gianluigi Donnarumma G 90 0 0.00 - n/a 0.0 7.0 60.0 31 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0099, quality 0.809)	`market_value_eur=46000000` `quality_factor=0.8089` `boost_factor=1.0099` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0094)	`blend_weight=0.0094` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.8948 -> 2.8864
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Nicolas Jackson, Ibrahim Mbaye', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.031}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	shots_faced: 9.8 -> 8.5 expected_saves: 2.4 -> 2.08 high_pressure_saves: 0.82 -> 0.71
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 89.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=3.0662`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=1.923`	-

Iliman Ndiaye F 83 0 0.30 0.13 127% 2 1.1 7.0 48.8 39 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0121, quality 0.859)	`market_value_eur=63000000` `quality_factor=0.8589` `boost_factor=1.0121` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0098)	`blend_weight=0.0098` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9269` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 2.3712 -> 2.357 wasFouled: 1.367 -> 1.3581 wonTackle: 1.1595 -> 1.1526 onTargetScoringAttempt: 0.7401 -> 0.7465
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Matty Cash, Tyrone Mings', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.289, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1315, 'skill_edge': 0.1295, 'height_edge': -0.04, 'attacker_skill': 0.8589, 'defender_skill': 0.5712, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Matty Cash', 'market_value': 19800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6892}, {'player': 'Tyrone Mings', 'market_value': 3200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4531}], 'xg_override': 0.2073}	totalShots: 1.7678 -> 2.0003 shotOffTarget: 1.0213 -> 1.1556 onTargetScoringAttempt: 0.7465 -> 0.8447 bigChanceMissed: 0.2446 -> 0.2768 goals: 0.2101 -> 0.2377 expectedGoals: 0.1832 -> 0.2073 expectedGoalsOnTarget: 0.1372 -> 0.1552
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.62 (squad xG sum 1.7834, xG scale 1.4686, xA scale 1.4686, team xA 1.82 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=2.619` `squad_xg_sum=1.7834` `squad_xa_sum=1.2382` `team_expected_assists=1.8184` `team_xa_to_xg_ratio=0.6943`	expected_goals: 0.2073 -> 0.3044 expected_assists: 0.131 -> 0.1924
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 82.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2624` `goal_rate=0.2377` `scorer_weight=0.3404`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.175` `assist_rate=0.2394` `provider_weight=0.2405`	-

Team totals 2 2.62 19 7.1

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Gerónimo Rulli	G	4.5m	11.5%	Market-value substitute prior
Nico O'Reilly	D	15.3m	25.3%	Market-value substitute prior
Matheus Nunes	D	25.5m	63.3%	Market-value substitute prior
Rayan Cherki	M	26.1m	53.7%	Market-value substitute prior
Elliot Anderson	M	23.8m	34.4%	Market-value substitute prior
Antoine Semenyo	F	27.1m	37.0%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Boubacar Kamara vs Enzo Fernández will be the pivotal duel. Total antagonist xG — Home: 0.90, Away: 1.46. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.5% / 50.5%, dominance ratio 0.46, key duel: Boubacar Kamara vs Enzo Fernández

Nicolas Jackson xG 0.38Ibrahim Mbaye xG 0.16Emiliano Buendía xG 0.14Phil Foden xG 0.21Erling Haaland xG 0.67Jérémy Doku xG 0.20

Summary

Antagonist matchup analysis for Aston Villa vs Man City. Most likely scoreline: 0-2. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Aston Villa 4W-1D-5L vs Man City over 10 meetings.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Boubacar Kamara vs Enzo Fernández will be the pivotal duel. Total antagonist xG — Home: 0.90, Away: 1.46. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Chelsea vs Tottenham

Premier League · 20261024 · 3-4-2-1 vs 4-2-3-1

Predicted 1-0Winner: ChelseaWinning H 1-0 (10.5%)Winning A 0-1 (6.1%)Confidence 0.75λ home/away 1.79 / 1.04Most-likely P 10.5%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Chelsea vs Tottenham. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 3-4-2-1 vs 4-2-3-1 (duel lambdas: Home 1.727, Away 1.081). Final calibrated Poisson lambdas: Home 1.789, Away 1.042 (most likely score 1-0).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.73 / 1.08 Final λ (H/A) 1.79 / 1.04

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Chelsea	Tottenham
League position	4.00	16.00
Points per game	1.63	1.09
Attack index	1.32	0.81
Defense (concede) index	0.94	1.17
Form multiplier	1.03	0.97
Standing λ multiplier	1.10	0.97

Lambda decomposition (how the goal rates were built)

Stage	Chelsea λ	Tottenham λ
Pre-competitive-floor	1.789	1.042
Pre-calibration (Micro-duels)	1.727	1.081
Final λ	1.789	1.042

Scoreline distribution & markets

Top 5 scorelines	P
1-1	11.1%
1-0	10.5%
2-1	9.8%
2-0	9.4%
0-1	6.1%

Home win	54.8%
Draw	23.3%
Away win	21.9%
Over 2.5	53.8%
BTTS yes	54.0%

Pregame fair line — favorite Chelsea (54.8%), fair total 2.83, fair spread 0.75

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Chelsea — projected line vs season baseline (3-4-2-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

João Pedro F 85 1 0.54 0.43 ok 3 2.1 7.0 60.0 27 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0126, quality 0.890)	`market_value_eur=92000000` `quality_factor=0.89` `boost_factor=1.0126` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0094)	`blend_weight=0.0094` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.9492` `prior_reliability=0.1333` `competition=Premier League`	totalShots: 2.625 -> 2.6405 goalAssist: 0.2805 -> 0.2868 totalCross: 0.5376 -> 0.5325
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Conor Gallagher, Micky van de Ven', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.299, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 1.0427, 'skill_edge': 0.0351, 'height_edge': -0.006, 'attacker_skill': 0.89, 'defender_skill': 0.8121, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Conor Gallagher', 'market_value': 31000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.761}, {'player': 'Micky van de Ven', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}], 'xg_override': 0.4265}	totalShots: 2.6405 -> 2.7532 shotOffTarget: 1.6171 -> 1.6862 onTargetScoringAttempt: 1.0117 -> 1.0549 expectedGoalsOnTarget: 0.5532 -> 0.5768 goals: 0.4442 -> 0.4632 bigChanceMissed: 0.4122 -> 0.4298 expectedGoals: 0.409 -> 0.4265
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.4265 -> 0.5385 expected_assists: 0.0664 -> 0.0906
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 83.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.4164` `goal_rate=0.4632` `scorer_weight=0.58`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0866` `assist_rate=0.2868` `provider_weight=0.1133`	-

Cole Palmer M 88 0 0.30 0.31 ok 3 2.4 7.0 61.6 34 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0153, quality 0.894)	`market_value_eur=101000000` `quality_factor=0.8936` `boost_factor=1.0153` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0108)	`blend_weight=0.0108` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.9809` `prior_reliability=0.1267` `competition=Premier League`	totalShots: 2.689 -> 2.7099 goals: 0.2541 -> 0.2625 onTargetScoringAttempt: 0.8536 -> 0.861 fouls: 0.9969 -> 0.9917
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Antonín Kinský', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run', 'duel_win_rate': 0.468, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0707, 'skill_edge': 0.0681, 'height_edge': -0.02, 'attacker_skill': 0.8993, 'defender_skill': 0.7479, 'attacker_role': 'LWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Antonín Kinský', 'market_value': 18900000, 'role': 'GK', 'price_index': 0.55, 'adjusted_quality': 0.7479}], 'xg_override': 0.2365}	aerialWon: 0.068 -> 1.2 totalShots: 2.7099 -> 2.9015 shotOffTarget: 1.8354 -> 1.9652 onTargetScoringAttempt: 0.861 -> 0.9219 goals: 0.2625 -> 0.2811 expectedGoals: 0.2209 -> 0.2365 bigChanceMissed: 0.1756 -> 0.188 expectedGoalsOnTarget: 0.1586 -> 0.1698
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2365 -> 0.2987 expected_assists: 0.1539 -> 0.2101
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 85.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2582` `goal_rate=0.2811` `scorer_weight=0.3452`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1895` `assist_rate=0.1962` `provider_weight=0.2537`	-

Jorrel Hato D 75 0 0.00 0.01 72% 0 0.2 6.7 50.6 34 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0144, quality 0.813)	`market_value_eur=47000000` `quality_factor=0.8129` `boost_factor=1.0144` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0115)	`blend_weight=0.0115` `history_matches=27` `season_overlap_discount=1.0` `per90_to_match_factor=0.8383` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 0.2239 -> 0.2327 wonTackle: 1.038 -> 1.0317 interceptionWon: 0.9281 -> 0.9231
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Omar Marmoush', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0388 -> 0.053
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 78.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0028` `goal_rate=0.0` `scorer_weight=0.0027`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0516` `assist_rate=0.2203` `provider_weight=0.0663`	-

Moisés Caicedo M 85 0 0.05 0.03 53% 1 0.7 7.0 57.0 26 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0143, quality 0.895)	`market_value_eur=104000000` `quality_factor=0.8945` `boost_factor=1.0143` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0011)	`blend_weight=0.0011` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.9456` `prior_reliability=0.0133` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Conor Gallagher', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.495, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.0664, 'skill_edge': 0.0612, 'height_edge': -0.016, 'attacker_skill': 0.8969, 'defender_skill': 0.761, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Conor Gallagher', 'market_value': 31000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.761}], 'xg_override': 0.0387}	aerialWon: 0.4665 -> 1.0 totalShots: 0.6983 -> 0.7447 shotOffTarget: 0.553 -> 0.5897 onTargetScoringAttempt: 0.1453 -> 0.1549
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0387 -> 0.0489 expected_assists: 0.044 -> 0.0601
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 86.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0477` `goal_rate=0.0451` `scorer_weight=0.0524`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0583` `assist_rate=0.0502` `provider_weight=0.0641`	-

Jordan Henderson M 82 0 0.10 0.02 493% 1 0.2 7.1 53.8 23 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9975, quality 0.437)	`market_value_eur=1300000` `quality_factor=0.4374` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Andy Robertson', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run', 'duel_win_rate': 0.378, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9676, 'skill_edge': -0.042, 'height_edge': 0.02, 'attacker_skill': 0.4374, 'defender_skill': 0.5308, 'attacker_role': 'RWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Andy Robertson', 'market_value': 7500000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.5308}], 'xg_override': 0.0762}	aerialWon: 0.8207 -> 1.1 totalShots: 0.9355 -> 0.9052 shotOffTarget: 0.6102 -> 0.5904 onTargetScoringAttempt: 0.3253 -> 0.3148
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0762 -> 0.0962 expected_assists: 0.1326 -> 0.181
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 78.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0917` `goal_rate=0.0951` `scorer_weight=0.1106`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1656` `assist_rate=0.1275` `provider_weight=0.176`	-

Pedro Neto F 83 0 0.17 0.09 84% 2 1.0 6.9 48.6 38 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0112, quality 0.848)	`market_value_eur=58000000` `quality_factor=0.8478` `boost_factor=1.0112` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0042)	`blend_weight=0.0042` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.923` `prior_reliability=0.06` `competition=Premier League`	onTargetScoringAttempt: 0.6583 -> 0.6641 totalShots: 1.7967 -> 1.802 totalCross: 4.3056 -> 4.3004
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Conor Gallagher, Micky van de Ven', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.226, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9354, 'skill_edge': 0.0161, 'height_edge': -0.06, 'attacker_skill': 0.8478, 'defender_skill': 0.8121, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Conor Gallagher', 'market_value': 31000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.761}, {'player': 'Micky van de Ven', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}], 'xg_override': 0.1375}	totalShots: 1.8025 -> 1.6861 shotOffTarget: 1.1384 -> 1.0649 onTargetScoringAttempt: 0.6641 -> 0.6212 expectedGoalsOnTarget: 0.3536 -> 0.3308 bigChanceMissed: 0.2309 -> 0.216 goals: 0.2192 -> 0.205 expectedGoals: 0.147 -> 0.1375
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1375 -> 0.1737 expected_assists: 0.1685 -> 0.2299
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 81.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1595` `goal_rate=0.205` `scorer_weight=0.2171`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.2054` `assist_rate=0.2612` `provider_weight=0.2874`	-

Levi Colwill D 88 0 0.00 0.00 72% 0 0.1 6.8 40.1 15 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0359, quality 0.840)	`market_value_eur=55000000` `quality_factor=0.8399` `boost_factor=1.0359` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0279)	`blend_weight=0.0279` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9828` `prior_reliability=0.12` `competition=Premier League`	wonTackle: 0.6005 -> 0.6294 wasFouled: 0.2437 -> 0.2521 totalShots: 0.3709 -> 0.3759
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Mateus Fernandes', 'matchup_zone': 'LW vs CB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0162 -> 0.0221
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 80.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0015` `goal_rate=0.0` `scorer_weight=0.0015`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0219` `assist_rate=0.0` `provider_weight=0.0177`	-

Maxence Lacroix D 88 0 0.10 0.07 47% 1 0.7 6.8 54.8 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0114, quality 0.861)	`market_value_eur=64000000` `quality_factor=0.8608` `boost_factor=1.0114` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.977` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.732 -> 0.7433
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Omar Marmoush', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0807 -> 0.1019 expected_assists: 0.0238 -> 0.0325
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 82.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0969` `goal_rate=0.0163` `scorer_weight=0.0815`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.032` `assist_rate=0.073` `provider_weight=0.0406`	-

Josh Acheampong D 83 0 0.03 0.00 3859% 0 0.0 6.6 35.8 29 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0110, quality 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.011` `reference_quality=0.505` `history_matches=23` `history_shrink=0.1786`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dominic Solanke', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0237 -> 0.0299
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 75.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0295` `goal_rate=0.0422` `scorer_weight=0.0374`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0145` `assist_rate=0.0` `provider_weight=0.012`	-

Mike Penders G 90 0 0.00 - n/a 0.0 7.0 6.0 12 FBref Prior G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0409, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0409` `reference_quality=0.505` `history_matches=1` `history_shrink=0.8333`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dominic Solanke, Omar Marmoush', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.081}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	shots_faced: 10.3 -> 9.9 expected_saves: 2.52 -> 2.42 high_pressure_saves: 0.86 -> 0.83
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 78.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=2.007`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=1.2634`	-

Morgan Rogers M 88 0 0.32 0.22 48% 3 2.4 7.1 61.1 35 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0120, quality 0.897)	`market_value_eur=115000000` `quality_factor=0.8968` `boost_factor=1.012` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0084)	`blend_weight=0.0084` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9771` `prior_reliability=0.1267` `competition=Premier League`	totalShots: 2.2805 -> 2.2873
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Conor Gallagher', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.532, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.1202, 'skill_edge': 0.0618, 'height_edge': 0.02, 'attacker_skill': 0.8983, 'defender_skill': 0.761, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Conor Gallagher', 'market_value': 31000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.761}], 'xg_override': 0.2531}	totalShots: 2.2873 -> 2.5622 shotOffTarget: 1.4027 -> 1.5713 onTargetScoringAttempt: 0.8747 -> 0.9798 aerialWon: 1.2666 -> 1.2 bigChanceMissed: 0.2915 -> 0.3265 goals: 0.2848 -> 0.319 expectedGoalsOnTarget: 0.2296 -> 0.2572 expectedGoals: 0.2259 -> 0.2531
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.79 (squad xG sum 1.4165, xG scale 1.2629, xA scale 1.3652, team xA 1.16 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.789` `squad_xg_sum=1.4165` `squad_xa_sum=0.8518` `team_expected_assists=1.1628` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2531 -> 0.3197 expected_assists: 0.1404 -> 0.1917
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 84.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2736` `goal_rate=0.319` `scorer_weight=0.3892`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1744` `assist_rate=0.1101` `provider_weight=0.1612`	-

Team totals 1 1.79 16 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Robert Sánchez	G	5.2m	14.7%	Market-value substitute prior
Reece James	D	19.5m	44.4%	Market-value substitute prior
Trevoh Chalobah	D	15.0m	36.3%	Market-value substitute prior
Marco Palestra	M	23.5m	56.6%	Market-value substitute prior
Valentín Barco	M	15.5m	72.1%	Market-value substitute prior
Estêvão	F	27.1m	63.9%	Market-value substitute prior

Tottenham — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Dominic Solanke F 79 0 0.23 0.14 62% 2 1.1 6.7 50.1 27 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0105, quality 0.694)	`market_value_eur=27000000` `quality_factor=0.6941` `boost_factor=1.0105` `reference_quality=0.505` `history_matches=22` `history_shrink=0.1852`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0032)	`blend_weight=0.0032` `history_matches=22` `season_overlap_discount=1.0` `per90_to_match_factor=0.8818` `prior_reliability=0.0267` `competition=Premier League`	wasFouled: 0.6913 -> 0.7032 totalShots: 2.1078 -> 2.1141 totalOffside: 0.4989 -> 0.5044 fouls: 1.6689 -> 1.6635
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Levi Colwill, Maxence Lacroix', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8561, 'skill_edge': -0.0839, 'height_edge': -0.014, 'attacker_skill': 0.6941, 'defender_skill': 0.8806, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Levi Colwill', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}, {'player': 'Maxence Lacroix', 'market_value': 64000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8862}], 'xg_override': 0.2792}	totalShots: 2.1141 -> 1.8099 shotOffTarget: 1.3919 -> 1.1916 onTargetScoringAttempt: 0.7201 -> 0.6165 bigChanceMissed: 0.5207 -> 0.4458 goals: 0.3387 -> 0.29 expectedGoals: 0.3261 -> 0.2792 expectedGoalsOnTarget: 0.2953 -> 0.2528
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.2792 -> 0.2266 expected_assists: 0.0564 -> 0.0458
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 79.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.2028` `goal_rate=0.29` `scorer_weight=0.234`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0448` `assist_rate=0.1656` `provider_weight=0.0573`	-

Omar Marmoush F 79 0 0.14 0.06 113% 2 1.0 6.8 39.2 31 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0157, quality 0.840)	`market_value_eur=55000000` `quality_factor=0.8399` `boost_factor=1.0157` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Levi Colwill, Maxence Lacroix', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9349, 'skill_edge': -0.0183, 'height_edge': -0.026, 'attacker_skill': 0.8399, 'defender_skill': 0.8806, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Levi Colwill', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}, {'player': 'Maxence Lacroix', 'market_value': 64000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8862}], 'xg_override': 0.1674}	totalShots: 1.8941 -> 1.7708 shotOffTarget: 1.3029 -> 1.2181 onTargetScoringAttempt: 0.5911 -> 0.5526 bigChanceMissed: 0.2281 -> 0.2133 goals: 0.209 -> 0.1954 expectedGoals: 0.1791 -> 0.1674 expectedGoalsOnTarget: 0.1082 -> 0.1012
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.1674 -> 0.1359 expected_assists: 0.0534 -> 0.0433
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 82.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1271` `goal_rate=0.1954` `scorer_weight=0.1534`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0424` `assist_rate=0.1416` `provider_weight=0.0541`	-

Conor Gallagher M 78 0 0.08 0.07 ok 1 0.5 6.8 49.1 30 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0073, quality 0.725)	`market_value_eur=31000000` `quality_factor=0.7249` `boost_factor=1.0073` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0024)	`blend_weight=0.0024` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.862` `prior_reliability=0.0333` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'João Pedro, Pedro Neto, Morgan Rogers', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.0977 -> 0.0793 expected_assists: 0.0617 -> 0.0501
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 78.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0762` `goal_rate=0.0879` `scorer_weight=0.074`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0489` `assist_rate=0.0725` `provider_weight=0.0549`	-

Mohammed Kudus F 74 0 0.09 0.04 114% 1 0.6 7.0 36.9 24 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0158, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0158` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0022)	`blend_weight=0.0022` `history_matches=25` `season_overlap_discount=1.0` `per90_to_match_factor=0.8269` `prior_reliability=0.02` `competition=Premier League`	totalCross: 4.5542 -> 4.5742
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Levi Colwill, Maxence Lacroix', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8809, 'skill_edge': -0.027, 'height_edge': -0.054, 'attacker_skill': 0.8206, 'defender_skill': 0.8806, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Levi Colwill', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}, {'player': 'Maxence Lacroix', 'market_value': 64000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8862}], 'xg_override': 0.1143}	totalShots: 1.3921 -> 1.2263 shotOffTarget: 0.9448 -> 0.8323 onTargetScoringAttempt: 0.4423 -> 0.3896 goals: 0.1616 -> 0.1424 expectedGoals: 0.1298 -> 0.1143 expectedGoalsOnTarget: 0.0792 -> 0.0698 bigChanceMissed: 0.0505 -> 0.0445
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.1143 -> 0.0928 expected_assists: 0.106 -> 0.086
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 81.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0886` `goal_rate=0.1424` `scorer_weight=0.1087`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0824` `assist_rate=0.2401` `provider_weight=0.1075`	-

Mateus Fernandes M 80 0 0.06 0.04 50% 1 0.8 6.9 57.6 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0113, quality 0.868)	`market_value_eur=68000000` `quality_factor=0.8677` `boost_factor=1.0113` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0068)	`blend_weight=0.0068` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.8858` `prior_reliability=0.1` `competition=Premier League`	totalCross: 1.7467 -> 1.7629 wasFouled: 0.9347 -> 0.9284 interceptionWon: 0.8562 -> 0.8504
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Levi Colwill', 'matchup_zone': 'LW vs CB', 'duel_win_rate': 0.381, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9422, 'skill_edge': -0.0033, 'height_edge': -0.036, 'attacker_skill': 0.8677, 'defender_skill': 0.8751, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Levi Colwill', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}], 'xg_override': 0.0758}	aerialWon: 0.4716 -> 1.0 totalShots: 1.0658 -> 1.0042 shotOffTarget: 0.7674 -> 0.723 onTargetScoringAttempt: 0.2984 -> 0.2812
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.0758 -> 0.0615 expected_assists: 0.0893 -> 0.0725
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 80.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0596` `goal_rate=0.0792` `scorer_weight=0.0632`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0699` `assist_rate=0.0868` `provider_weight=0.0712`	-

Sandro Tonali M 86 0 0.06 0.05 ok 1 1.2 7.3 55.6 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0121, quality 0.884)	`market_value_eur=83000000` `quality_factor=0.8845` `boost_factor=1.0121` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0083)	`blend_weight=0.0083` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9503` `prior_reliability=0.12` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Morgan Rogers', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.391, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9576, 'skill_edge': -0.0049, 'height_edge': -0.024, 'attacker_skill': 0.8875, 'defender_skill': 0.8983, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Morgan Rogers', 'market_value': 115000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.8983}], 'xg_override': 0.0678}	aerialWon: 0.5761 -> 1.1 totalShots: 1.1732 -> 1.1235 shotOffTarget: 0.8356 -> 0.8002 onTargetScoringAttempt: 0.3359 -> 0.3217
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.0678 -> 0.055 expected_assists: 0.1583 -> 0.1285
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 85.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0535` `goal_rate=0.0851` `scorer_weight=0.0631`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1206` `assist_rate=0.1196` `provider_weight=0.1046`	-

Andy Robertson D 82 0 0.04 0.03 39% 1 0.3 6.8 39.9 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9995, quality 0.493)	`market_value_eur=7500000` `quality_factor=0.4927` `boost_factor=0.9995` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0105)	`blend_weight=0.0105` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.906` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 0.2132 -> 0.2222 totalCross: 4.9744 -> 4.9669
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Jordan Henderson', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.0549 -> 0.0446 expected_assists: 0.0879 -> 0.0714
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 85.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0436` `goal_rate=0.0598` `scorer_weight=0.0467`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0689` `assist_rate=0.2965` `provider_weight=0.0893`	-

Micky van de Ven D 88 0 0.06 0.05 ok 1 0.3 6.9 53.9 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0103, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0103` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0047)	`blend_weight=0.0047` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.9798` `prior_reliability=0.0667` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'João Pedro', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.078 -> 0.0633
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 81.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0613` `goal_rate=0.0131` `scorer_weight=0.0506`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0084` `assist_rate=0.005` `provider_weight=0.0077`	-

Jan Paul van Hecke D 90 0 0.09 0.07 31% 1 0.5 7.2 58.3 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0112, quality 0.863)	`market_value_eur=65000000` `quality_factor=0.8627` `boost_factor=1.0112` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9979` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.2641 -> 1.2572 totalCross: 0.6474 -> 0.6416
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'João Pedro', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.1148 -> 0.0932 expected_assists: 0.0723 -> 0.0587
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 81.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.089` `goal_rate=0.1361` `scorer_weight=0.1052`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.057` `assist_rate=0.0272` `provider_weight=0.047`	-

Archie Gray M 83 0 0.04 0.04 ok 1 0.4 6.8 46.2 37 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0103, quality 0.746)	`market_value_eur=34000000` `quality_factor=0.7455` `boost_factor=1.0103` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0105)	`blend_weight=0.0105` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.9261` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 0.9752 -> 0.9879 totalShots: 0.7225 -> 0.7149
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Cole Palmer', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	expected_goals: 0.0545 -> 0.0442 expected_assists: 0.0599 -> 0.0486
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 77.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0432` `goal_rate=0.052` `scorer_weight=0.0431`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0474` `assist_rate=0.0829` `provider_weight=0.0588`	-

Antonín Kinský G 90 0 0.00 - n/a 0.0 7.0 29.2 32 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0091, quality 0.620)	`market_value_eur=18900000` `quality_factor=0.6201` `boost_factor=1.0091` `reference_quality=0.505` `history_matches=14` `history_shrink=0.2632`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0228)	`blend_weight=0.0228` `history_matches=14` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	wasFouled: 0.2807 -> 0.2743 saves: 2.7473 -> 2.7417
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'João Pedro, Morgan Rogers', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.7268}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.04 (squad xG sum 1.2837, xG scale 0.8117, xA scale 0.8117, team xA 0.75 = 0.72 x lambda)	`scoreline_reset=true` `team_lambda=1.042` `squad_xg_sum=1.2837` `squad_xa_sum=0.9299` `team_expected_assists=0.7549` `team_xa_to_xg_ratio=0.7244`	shots_faced: 16.4 -> 17.0 expected_saves: 4.01 -> 4.16 high_pressure_saves: 1.38 -> 1.43
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 77.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.0921`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.7886`	-

Team totals 0 1.04 15 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Guglielmo Vicario	G	5.0m	13.9%	Market-value substitute prior
Pedro Porro	D	15.0m	24.6%	Market-value substitute prior
Destiny Udogie	D	14.3m	62.3%	Market-value substitute prior
Xavi Simons	M	23.4m	56.3%	Market-value substitute prior
Lucas Bergvall	M	23.4m	33.5%	Market-value substitute prior
Sávio	F	26.9m	63.0%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Morgan Rogers vs Sandro Tonali will be the pivotal duel. Total antagonist xG — Home: 1.17, Away: 0.70. Home danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.9% / 50.1%, dominance ratio 0.49, key duel: Morgan Rogers vs Sandro Tonali

João Pedro xG 0.43Pedro Neto xG 0.14Cole Palmer xG 0.24Mateus Fernandes xG 0.08Sandro Tonali xG 0.07Omar Marmoush xG 0.17

Summary

Antagonist matchup analysis for Chelsea vs Tottenham. Most likely scoreline: 1-0. Lambdas derived from 6 home and 5 away individual player duels. Head-to-head: Chelsea 7W-1D-2L vs Tottenham over 10 meetings.

Tactical parity between 3-4-2-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Morgan Rogers vs Sandro Tonali will be the pivotal duel. Total antagonist xG — Home: 1.17, Away: 0.70. Home danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Valencia vs Villarreal

LaLiga · 20261024 · 4-2-3-1 vs 4-4-2

Predicted 0-1Winner: VillarrealWinning H 1-0 (8.5%)Winning A 0-1 (13.7%)Confidence 0.74λ home/away 0.90 / 1.45Most-likely P 13.7%

Actual vs predicted: result not available yet (upcoming fixture).

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Valencia vs Villarreal. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-4-2 (duel lambdas: Home 0.919, Away 1.421). Final calibrated Poisson lambdas: Home 0.899, Away 1.451 (most likely score 0-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.92 / 1.42 Final λ (H/A) 0.90 / 1.45

FBref Team Priors: Valencia (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.328) vs Villarreal (Gls/90: 1.3333333333333333, GA/90: 1.33 → E[λ]: 0.326) | Blend Weight: 0.228

Modeling Pipeline Stages (5 layers)

1. XGBoost player regressions for volume & event rates with market-value quality scaling
2. Multi-source prior blending (FBref 2026-2027 tables + Sofascore season history)
3. Antagonist formation duel matrix resolving 1v1 and zonal matchups
4. Team-level prior calibration (FBref possession and attack/defense efficiencies)
5. Bivariate Poisson matrix with Dixon-Coles low-score correction

Standing & form context

Metric	Valencia	Villarreal
League position	19.00	12.00
Points per game	0.94	1.14
Attack index	0.80	0.93
Defense (concede) index	0.93	1.09
Form multiplier	0.99	1.01
Standing λ multiplier	0.89	1.01

Lambda decomposition (how the goal rates were built)

Stage	Valencia λ	Villarreal λ
FBref Squad Prior E[λ] (weight 0.228)	0.328	0.326
Pre-competitive-floor	0.899	1.451
Pre-calibration (Micro-duels)	0.919	1.421
Final λ	0.899	1.451

Scoreline distribution & markets

Top 5 scorelines	P
0-1	13.7%
1-1	12.5%
0-2	10.0%
0-0	9.6%
1-2	9.0%

Home win	23.2%
Draw	26.9%
Away win	49.9%
Over 2.5	41.7%
BTTS yes	45.5%

Pregame fair line — favorite Villarreal (49.9%), fair total 2.35, fair spread -0.55

Projected players vs season baseline

Proj = projected for this match · Season = this season's per-game average from match data · deviation badge compares projected xG to the player's season xG/game.

Valencia — projected line vs season baseline (4-2-3-1)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Stole Dimitrievski G 90 0 0.00 - n/a 0.0 6.9 65.3 31 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9970, quality 0.437)	`market_value_eur=2100000` `quality_factor=0.4374` `boost_factor=0.997` `reference_quality=0.505` `history_matches=29` `history_shrink=0.1471`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0191)	`blend_weight=0.0191` `history_matches=29` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.9671 -> 2.9614 wasFouled: 0.2806 -> 0.2752
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alberto Moleiro, Ayoze Pérez', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.4207}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	shots_faced: 13.5 -> 13.8 expected_saves: 3.3 -> 3.38 high_pressure_saves: 1.14 -> 1.16
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=0.9718`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.6412`	-

Arnaut Danjuma F 82 0 0.13 0.08 65% 1 1.0 6.9 54.1 33 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=2800000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0094)	`blend_weight=0.0094` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9113` `prior_reliability=0.1267` `competition=La Liga`	totalShots: 1.5886 -> 1.6059 wasFouled: 0.8962 -> 0.9058 fouls: 0.6665 -> 0.6737
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Renato Veiga, Alexander Freeman', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.7654, 'skill_edge': -0.1156, 'height_edge': -0.044, 'attacker_skill': 0.4374, 'defender_skill': 0.6943, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Renato Veiga', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Alexander Freeman', 'market_value': 13800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.615}], 'xg_override': 0.1315}	totalShots: 1.6059 -> 1.2292 shotOffTarget: 0.9765 -> 0.7474 onTargetScoringAttempt: 0.6155 -> 0.4711 bigChanceMissed: 0.4954 -> 0.3792 goals: 0.1894 -> 0.145 expectedGoals: 0.1718 -> 0.1315 expectedGoalsOnTarget: 0.0936 -> 0.0716
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 75.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1252` `goal_rate=0.145` `scorer_weight=0.1438`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0922` `assist_rate=0.0377` `provider_weight=0.0774`	-

Luis Rioja F 78 0 0.11 0.05 129% 1 0.8 6.7 59.1 31 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.437)	`market_value_eur=1900000` `quality_factor=0.4374` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Renato Veiga, Alexander Freeman', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.7419, 'skill_edge': -0.1156, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.6943, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Renato Veiga', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Alexander Freeman', 'market_value': 13800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.615}], 'xg_override': 0.1126}	totalShots: 1.2095 -> 0.8973 shotOffTarget: 0.8046 -> 0.5969 onTargetScoringAttempt: 0.4049 -> 0.3004 goals: 0.1563 -> 0.116 expectedGoals: 0.1518 -> 0.1126 bigChanceMissed: 0.1 -> 0.0742 expectedGoalsOnTarget: 0.088 -> 0.0653
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 77.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1083` `goal_rate=0.116` `scorer_weight=0.117`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0763` `assist_rate=0.137` `provider_weight=0.0993`	-

Javier Guerra M 83 0 0.19 0.11 67% 3 1.2 6.9 60.3 34 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0054, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0054` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0117)	`blend_weight=0.0117` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9211` `prior_reliability=0.18` `competition=La Liga`	totalShots: 2.1287 -> 2.116 fouls: 0.7672 -> 0.7582 onTargetScoringAttempt: 0.6818 -> 0.6738
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Sergi Cardona', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.546, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0965, 'skill_edge': 0.0616, 'height_edge': 0.004, 'attacker_skill': 0.6858, 'defender_skill': 0.5489, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Sergi Cardona', 'market_value': 8600000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.5489}], 'xg_override': 0.1839}	aerialWon: 0.7275 -> 1.2 totalShots: 2.1207 -> 2.3253 shotOffTarget: 1.4469 -> 1.5865 onTargetScoringAttempt: 0.6738 -> 0.7388 bigChanceMissed: 0.3274 -> 0.359 goals: 0.2202 -> 0.2414 expectedGoals: 0.1677 -> 0.1839 expectedGoalsOnTarget: 0.1444 -> 0.1583
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 82.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1706` `goal_rate=0.2414` `scorer_weight=0.2331`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1125` `assist_rate=0.1179` `provider_weight=0.1197`	-

Dani Raba F 62 0 0.15 0.04 297% 2 0.3 6.8 12.8 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9952, quality 0.437)	`market_value_eur=1000000` `quality_factor=0.4374` `boost_factor=0.9952` `reference_quality=0.505` `history_matches=16` `history_shrink=0.2381`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0010)	`blend_weight=0.001` `history_matches=16` `season_overlap_discount=1.0` `per90_to_match_factor=0.6841` `prior_reliability=0.0067` `competition=La Liga`	totalCross: 0.7902 -> 0.7965 totalShots: 1.5953 -> 1.6007
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Renato Veiga, Alexander Freeman', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.8007, 'skill_edge': -0.1156, 'height_edge': -0.02, 'attacker_skill': 0.4374, 'defender_skill': 0.6943, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Renato Veiga', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Alexander Freeman', 'market_value': 13800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.615}], 'xg_override': 0.1496}	totalShots: 1.6007 -> 1.2817 shotOffTarget: 0.9174 -> 0.7346 onTargetScoringAttempt: 0.6772 -> 0.5422 bigChanceMissed: 0.2281 -> 0.1826 expectedGoalsOnTarget: 0.2092 -> 0.1675 goals: 0.1963 -> 0.1572 expectedGoals: 0.1868 -> 0.1496
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 74.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1412` `goal_rate=0.1572` `scorer_weight=0.158`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0603` `assist_rate=0.14` `provider_weight=0.0777`	-

Guido Rodríguez M 85 0 0.04 0.04 ok 1 0.6 7.0 61.3 27 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9973, quality 0.445)	`market_value_eur=3600000` `quality_factor=0.4449` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0131)	`blend_weight=0.0131` `history_matches=28` `season_overlap_discount=1.0` `per90_to_match_factor=0.9426` `prior_reliability=0.1333` `competition=La Liga`	interceptionWon: 1.4688 -> 1.4805 wonTackle: 1.8352 -> 1.8297 fouls: 1.463 -> 1.4685
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pape Gueye', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.237, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7604, 'skill_edge': -0.155, 'height_edge': -0.008, 'attacker_skill': 0.4527, 'defender_skill': 0.7972, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pape Gueye', 'market_value': 39000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.7972}], 'xg_override': 0.0345}	totalShots: 0.659 -> 0.5011 shotOffTarget: 0.4627 -> 0.3518 aerialWon: 1.1207 -> 1.2 onTargetScoringAttempt: 0.1963 -> 0.1493 goals: 0.0636 -> 0.0484 expectedGoals: 0.0454 -> 0.0345 expectedGoalsOnTarget: 0.0384 -> 0.0292
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 78.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0345` `goal_rate=0.0484` `scorer_weight=0.0409`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0327` `assist_rate=0.054` `provider_weight=0.0415`	-

Pepelu M 84 0 0.02 0.08 70% 0 0.4 6.9 54.5 39 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9995, quality 0.490)	`market_value_eur=7300000` `quality_factor=0.4903` `boost_factor=0.9995` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pape Gueye', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.261, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7954, 'skill_edge': -0.1312, 'height_edge': -0.008, 'attacker_skill': 0.5057, 'defender_skill': 0.7972, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pape Gueye', 'market_value': 39000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.7972}], 'xg_override': 0.0235}	aerialWon: 0.4131 -> 1.2 totalShots: 0.5179 -> 0.412 shotOffTarget: 0.4039 -> 0.3213 onTargetScoringAttempt: 0.114 -> 0.0907 goals: 0.0418 -> 0.0332 expectedGoals: 0.0295 -> 0.0235
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 76.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0236` `goal_rate=0.0332` `scorer_weight=0.0271`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0324` `assist_rate=0.0456` `provider_weight=0.0382`	-

José Luis Gayà D 82 0 0.05 0.03 63% 1 0.4 6.8 56.6 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9982, quality 0.454)	`market_value_eur=4300000` `quality_factor=0.4535` `boost_factor=0.9982` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0039)	`blend_weight=0.0039` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9138` `prior_reliability=0.0533` `competition=La Liga`	wasFouled: 0.6159 -> 0.6225
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Ayoze Pérez', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 80.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0465` `goal_rate=0.0063` `scorer_weight=0.0381`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0622` `assist_rate=0.0368` `provider_weight=0.0514`	-

Justin De Haas D 81 0 0.00 0.00 60% 0 0.1 6.8 42.8 8 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9985, quality 0.495)	`market_value_eur=7700000` `quality_factor=0.4951` `boost_factor=0.9985` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0108)	`blend_weight=0.0108` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.905` `prior_reliability=0.0333` `competition=La Liga`	fouls: 0.5004 -> 0.5146 interceptionWon: 1.0433 -> 1.032 wonTackle: 0.6238 -> 0.617
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Ayoze Pérez', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 76.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0035` `goal_rate=0.0` `scorer_weight=0.0033`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0126` `assist_rate=0.2264` `provider_weight=0.0159`	-

César Tárrega D 81 0 0.03 0.02 49% 1 0.3 6.8 50.7 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0003, quality 0.514)	`market_value_eur=9300000` `quality_factor=0.5142` `boost_factor=1.0003` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0151)	`blend_weight=0.0151` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9043` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.1654 -> 1.1523 wonTackle: 0.8148 -> 0.8253 totalShots: 0.508 -> 0.514
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Ayoze Pérez', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 75.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0282` `goal_rate=0.0` `scorer_weight=0.0229`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0062` `assist_rate=0.0` `provider_weight=0.0055`	-

Pablo Maffeo D 83 0 0.02 0.01 55% 1 0.3 6.8 61.2 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=2400000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0039)	`blend_weight=0.0039` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9249` `prior_reliability=0.0533` `competition=La Liga`	totalCross: 2.8595 -> 2.871
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Santi Comesaña', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.90 (squad xG sum 0.8835, xG scale 1.0175, xA scale 1.0175, team xA 0.62 = 0.69 x lambda)	`scoreline_reset=true` `team_lambda=0.899` `squad_xg_sum=0.8835` `squad_xa_sum=0.6086` `team_expected_assists=0.6192` `team_xa_to_xg_ratio=0.6888`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 82.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.02` `goal_rate=0.0012` `scorer_weight=0.0162`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0625` `assist_rate=0.0744` `provider_weight=0.0708`	-

Team totals 0 0.90 14 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Kayne van Oevelen	G	4.5m	11.1%	Market-value substitute prior
Arnau Martínez	D	13.9m	22.5%	Market-value substitute prior
José Copete	D	13.7m	30.2%	Market-value substitute prior
Harvey Elliott	M	22.8m	53.5%	Market-value substitute prior
Filip Ugrinić	M	29.8m	43.8%	Market-value substitute prior
Hugo Duro	F	22.6m	59.9%	Market-value substitute prior

Villarreal — projected line vs season baseline (4-4-2)

Player Pos Min Proj G Proj xG Season xG/g Proj Sh Season Sh/g Proj Rtg Season Rtg Rec Model / FBref Prior

Gerard Moreno F 77 0 0.24 0.23 ok 2 1.3 7.0 57.3 28 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9971, quality 0.437)	`market_value_eur=2400000` `quality_factor=0.4374` `boost_factor=0.9971` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0093)	`blend_weight=0.0093` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.852` `prior_reliability=0.1` `competition=La Liga`	fouls: 0.6411 -> 0.651 wasFouled: 0.7311 -> 0.7243
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Justin De Haas, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.86, 'skill_edge': -0.0452, 'height_edge': -0.05, 'attacker_skill': 0.4374, 'defender_skill': 0.5379, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Justin De Haas', 'market_value': 7700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5256}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.2345}	totalShots: 2.0033 -> 1.7228 shotOffTarget: 1.2136 -> 1.0437 onTargetScoringAttempt: 0.7897 -> 0.6791 expectedGoalsOnTarget: 0.4008 -> 0.3447 goals: 0.2888 -> 0.2484 expectedGoals: 0.2727 -> 0.2345 bigChanceMissed: 0.2678 -> 0.2303
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 81.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2128` `goal_rate=0.2484` `scorer_weight=0.251`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1032` `assist_rate=0.0` `provider_weight=0.0871`	-

Ayoze Pérez F 73 0 0.30 0.26 ok 2 1.2 6.9 57.9 29 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9985, quality 0.467)	`market_value_eur=5400000` `quality_factor=0.4671` `boost_factor=0.9985` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0089)	`blend_weight=0.0089` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.8112` `prior_reliability=0.1067` `competition=La Liga`	wasFouled: 1.4436 -> 1.4533 totalShots: 2.2772 -> 2.284 onTargetScoringAttempt: 0.8713 -> 0.877 totalOffside: 0.5744 -> 0.5693
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Justin De Haas, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8797, 'skill_edge': -0.0319, 'height_edge': -0.05, 'attacker_skill': 0.4671, 'defender_skill': 0.5379, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Justin De Haas', 'market_value': 7700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5256}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.2934}	totalShots: 2.284 -> 2.0092 shotOffTarget: 1.4059 -> 1.2368 onTargetScoringAttempt: 0.877 -> 0.7715 bigChanceMissed: 0.8574 -> 0.7543 goals: 0.3619 -> 0.3184 expectedGoals: 0.3335 -> 0.2934 expectedGoalsOnTarget: 0.2642 -> 0.2324
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	expected_goals: 0.2934 -> 0.2994
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 79.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2587` `goal_rate=0.3184` `scorer_weight=0.3212`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0642` `assist_rate=0.2563` `provider_weight=0.083`	-

Alberto Moleiro F 80 1 0.39 0.16 150% 3 1.1 7.2 61.1 41 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0098, quality 0.837)	`market_value_eur=54000000` `quality_factor=0.837` `boost_factor=1.0098` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0068)	`blend_weight=0.0068` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=0.8926` `prior_reliability=0.1067` `competition=La Liga`	totalShots: 2.8155 -> 2.7964 onTargetScoringAttempt: 1.266 -> 1.2574 wonTackle: 0.6333 -> 0.6404 totalCross: 3.5658 -> 3.5605
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Justin De Haas, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.275, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1097, 'skill_edge': 0.1346, 'height_edge': -0.06, 'attacker_skill': 0.837, 'defender_skill': 0.5379, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Justin De Haas', 'market_value': 7700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5256}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.386}	totalShots: 2.8069 -> 3.1148 shotOffTarget: 1.5495 -> 1.7195 onTargetScoringAttempt: 1.2574 -> 1.3953 bigChanceMissed: 0.5903 -> 0.6551 expectedGoalsOnTarget: 0.3718 -> 0.4126 expectedGoals: 0.3478 -> 0.386 goals: 0.3142 -> 0.3487
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	expected_goals: 0.386 -> 0.3937
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 79.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3254` `goal_rate=0.3487` `scorer_weight=0.36`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1972` `assist_rate=0.3282` `provider_weight=0.2746`	-

Pape Gueye M 79 0 0.15 0.15 ok 2 1.2 7.1 62.2 30 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0092, quality 0.775)	`market_value_eur=39000000` `quality_factor=0.7754` `boost_factor=1.0092` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0148)	`blend_weight=0.0148` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.8826` `prior_reliability=0.2` `competition=La Liga`	totalShots: 1.3332 -> 1.3265 totalCross: 0.6713 -> 0.6657 fouls: 0.8141 -> 0.8195
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Guido Rodríguez', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.613, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2396, 'skill_edge': 0.155, 'height_edge': 0.008, 'attacker_skill': 0.7972, 'defender_skill': 0.4527, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Guido Rodríguez', 'market_value': 3600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4527}], 'xg_override': 0.1442}	aerialWon: 0.394 -> 1.2 totalShots: 1.3299 -> 1.6485 shotOffTarget: 0.8198 -> 1.0162 onTargetScoringAttempt: 0.5101 -> 0.6323 goals: 0.1426 -> 0.1768 expectedGoals: 0.1163 -> 0.1442 expectedGoalsOnTarget: 0.0843 -> 0.1045 bigChanceMissed: 0.0558 -> 0.0692
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 80.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1368` `goal_rate=0.1768` `scorer_weight=0.1718`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1015` `assist_rate=0.083` `provider_weight=0.0919`	-

Santi Comesaña M 70 0 0.06 0.08 ok 1 0.4 6.9 62.8 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0000, quality 0.503)	`market_value_eur=8400000` `quality_factor=0.5035` `boost_factor=1.0` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0101)	`blend_weight=0.0101` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.779` `prior_reliability=0.1467` `competition=La Liga`	totalShots: 0.6483 -> 0.6417 fouls: 1.4729 -> 1.4795 wonTackle: 0.7787 -> 0.7852 wasFouled: 0.8838 -> 0.8784
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pablo Maffeo', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel', 'duel_win_rate': 0.548, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1298, 'skill_edge': 0.0323, 'height_edge': 0.056, 'attacker_skill': 0.5146, 'defender_skill': 0.4428, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Pablo Maffeo', 'market_value': 2400000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4428}], 'xg_override': 0.0633}	aerialWon: 0.2212 -> 1.2 totalShots: 0.6464 -> 0.7303 shotOffTarget: 0.4687 -> 0.5295 onTargetScoringAttempt: 0.1777 -> 0.2008 bigChanceMissed: 0.1353 -> 0.1529 expectedGoalsOnTarget: 0.0872 -> 0.0985 goals: 0.0607 -> 0.0686 expectedGoals: 0.056 -> 0.0633
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 79.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0626` `goal_rate=0.0686` `scorer_weight=0.0676`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0733` `assist_rate=0.0749` `provider_weight=0.0763`	-

Ilias Akhomach F 73 0 0.11 0.06 78% 2 1.0 7.0 51.5 28 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0014, quality 0.535)	`market_value_eur=11100000` `quality_factor=0.5353` `boost_factor=1.0014` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0033)	`blend_weight=0.0033` `history_matches=28` `season_overlap_discount=1.0` `per90_to_match_factor=0.8103` `prior_reliability=0.0333` `competition=La Liga`	totalCross: 2.5731 -> 2.6072 totalShots: 1.6345 -> 1.6291 wasFouled: 1.7183 -> 1.7233
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Justin De Haas, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9101, 'skill_edge': -0.0012, 'height_edge': -0.06, 'attacker_skill': 0.5353, 'defender_skill': 0.5379, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Justin De Haas', 'market_value': 7700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5256}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.107}	totalShots: 1.6326 -> 1.4858 shotOffTarget: 1.0423 -> 0.9486 onTargetScoringAttempt: 0.5903 -> 0.5372 goals: 0.187 -> 0.1702 expectedGoals: 0.1176 -> 0.107 bigChanceMissed: 0.0639 -> 0.0582
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 75.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1034` `goal_rate=0.1702` `scorer_weight=0.1365`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=1` `assist_probability=0.134` `assist_rate=0.2277` `provider_weight=0.1799`	-

Sergi Cardona D 86 0 0.03 0.01 104% 1 0.4 6.7 46.9 33 FBref Prior D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0000, quality 0.506)	`market_value_eur=8600000` `quality_factor=0.5059` `boost_factor=1.0` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Javier Guerra', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 79.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0252` `goal_rate=0.0491` `scorer_weight=0.0319`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1191` `assist_rate=0.0095` `provider_weight=0.1014`	-

Renato Veiga D 90 0 0.02 0.01 95% 1 0.2 7.0 57.5 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0068, quality 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.0068` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0144)	`blend_weight=0.0144` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9983` `prior_reliability=0.2` `competition=La Liga`	wonTackle: 0.5842 -> 0.5758
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dani Raba', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 78.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0188` `goal_rate=0.0` `scorer_weight=0.0152`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0873` `assist_rate=0.0917` `provider_weight=0.0927`	-

Juan Foyth D 80 0 0.04 0.02 64% 1 0.3 7.0 54.2 13 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0001, quality 0.506)	`market_value_eur=8600000` `quality_factor=0.5059` `boost_factor=1.0001` `reference_quality=0.505` `history_matches=18` `history_shrink=0.2174`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0283)	`blend_weight=0.0283` `history_matches=18` `season_overlap_discount=1.0` `per90_to_match_factor=0.8936` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.1638 -> 1.1898 totalShots: 0.4912 -> 0.5109 wonTackle: 0.954 -> 0.9691 fouls: 0.7488 -> 0.7361 wasFouled: 0.2827 -> 0.2915 onTargetScoringAttempt: 0.1157 -> 0.1208
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dani Raba', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 79.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0397` `goal_rate=0.0` `scorer_weight=0.0324`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.043` `assist_rate=0.0` `provider_weight=0.0352`	-

Péter Gulácsi G 90 0 0.00 - n/a 0.0 7.1 33.8 11 FBref Prior G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9899, quality 0.437)	`market_value_eur=970000` `quality_factor=0.4374` `boost_factor=0.9899` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Javier Guerra, Dani Raba', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.919}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	shots_faced: 8.7 -> 8.5 expected_saves: 2.13 -> 2.08 high_pressure_saves: 0.74 -> 0.72
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 82.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.5114`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=1.1097`	-

Alexander Freeman D 90 0 0.02 0.01 241% 0 0.1 6.9 38.4 29 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0042, quality 0.566)	`market_value_eur=13800000` `quality_factor=0.566` `boost_factor=1.0042` `reference_quality=0.505` `history_matches=17` `history_shrink=0.2273`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dani Raba', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 1.4221, xG scale 1.0203, xA scale 1.0203, team xA 1.08 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.451` `squad_xg_sum=1.4221` `squad_xa_sum=1.0618` `team_expected_assists=1.0833` `team_xa_to_xg_ratio=0.7466`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 81.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0225` `goal_rate=0.0` `scorer_weight=0.0182`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0482` `assist_rate=0.0` `provider_weight=0.0395`	-

Team totals 1 1.45 16 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Luiz Júnior	G	4.8m	12.9%	Market-value substitute prior
Carlos Romero	D	14.5m	23.6%	Market-value substitute prior
Santiago Mouriño	D	14.3m	23.2%	Market-value substitute prior
Carlos Maciá	M	23.3m	70.3%	Market-value substitute prior
Nathan-Dylan Saliba	M	22.5m	52.2%	Market-value substitute prior
Georges Mikautadze	F	26.7m	36.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Javier Guerra vs Pape Gueye will be the pivotal duel. Total antagonist xG — Home: 0.64, Away: 1.23. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.2% / 50.8%, dominance ratio 0.47, key duel: Javier Guerra vs Pape Gueye

Javier Guerra xG 0.18Dani Raba xG 0.15Arnaut Danjuma xG 0.13Ayoze Pérez xG 0.29Alberto Moleiro xG 0.39Gerard Moreno xG 0.23

Summary

Antagonist matchup analysis for Valencia vs Villarreal. Most likely scoreline: 0-1. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Valencia 2W-3D-5L vs Villarreal over 10 meetings.

4-2-3-1 creates structural superiority against 4-4-2. Home team should exploit wider spaces and numerical advantages in transition. Midfield is evenly contested — Javier Guerra vs Pape Gueye will be the pivotal duel. Total antagonist xG — Home: 0.64, Away: 1.23. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Generated 2026-10-24 13:38:10 UTC · Soccer prediction reporting