Soccer predictions: actual data vs predicted data

Slate 20261106 · 2 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
Sevilla vs Alavés LaLiga	2-1	Sevilla	42.8% / 24.4% / 32.9%	57.3%	59.9%	0.66	1.60 / 1.38	-	pending
Everton vs Coventry Premier League	1-0	Everton	55.0% / 23.5% / 21.4%	52.6%	52.9%	0.69	1.77 / 1.01	-	pending

Match detail

Sevilla vs Alavés

LaLiga · 20261106 · 4-2-3-1 vs 5-3-2

Predicted 2-1Winner: SevillaWinning H 2-1 (9.0%)Winning A 1-2 (7.7%)Confidence 0.66λ home/away 1.60 / 1.38Most-likely P 9.0%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Sevilla vs Alavés. 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 5-3-2 (duel lambdas: Home 1.562, Away 1.297). Final calibrated Poisson lambdas: Home 1.604, Away 1.379 (most likely score 2-1).

Home Starters 11/11 XGBoost (6 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.56 / 1.30 Final λ (H/A) 1.60 / 1.38

FBref Team Priors: Sevilla (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 2.474) vs Deportivo Alavés (Gls/90: 1.6666666666666667, GA/90: 1.67 → E[λ]: 2.469) | 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	Sevilla	Alavés
League position	6.00	10.00
Points per game	1.58	1.19
Attack index	1.03	0.91
Defense (concede) index	0.97	1.03
Form multiplier	1.02	0.98
Standing λ multiplier	1.00	0.97

Lambda decomposition (how the goal rates were built)

Stage	Sevilla λ	Alavés λ
FBref Squad Prior E[λ] (weight 0.228)	2.474	2.469
Pre-competitive-floor	1.493	1.447
Pre-calibration (Micro-duels)	1.562	1.297
Final λ	1.604	1.379

competition calibration scale 1.015competition observed total goals 2.984quality gap applied Truemismatch score pressure applied Falsecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
1-1	11.3%
2-1	9.0%
1-0	8.0%
1-2	7.7%
0-1	6.9%

Home win	42.8%
Draw	24.4%
Away win	32.9%
Over 2.5	57.3%
BTTS yes	59.9%

Pregame fair line — favorite Sevilla (42.8%), fair total 2.98, fair spread 0.23

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.

Sevilla — 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

Odysseas Vlachodimos G 90 0 0.00 - n/a 0.0 6.8 60.6 34 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 0.9980, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.998` `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=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.7997 -> 2.8069
`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 Boyé, Ángel Pérez', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2967}`	-
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	shots_faced: 12.3 -> 13.1 expected_saves: 3.01 -> 3.21 high_pressure_saves: 1.04 -> 1.1
`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: 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=1.6415`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=1.2113`	-

Kike Salas D 90 0 0.11 0.06 81% 1 0.8 6.9 63.2 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 1.0030, quality 0.584)	`market_value_eur=15400000` `quality_factor=0.5835` `boost_factor=1.003` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0111)	`blend_weight=0.0111` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.9988` `prior_reliability=0.1333` `competition=La Liga`	wasFouled: 0.548 -> 0.5586 totalShots: 0.9535 -> 0.9599 onTargetScoringAttempt: 0.5622 -> 0.556
`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 Boyé', '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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0587 -> 0.1058 expected_assists: 0.0412 -> 0.0662
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1004` `goal_rate=0.0336` `scorer_weight=0.0846`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.0641` `assist_rate=0.0` `provider_weight=0.053`	-

Gabriel Suazo D 88 0 0.01 0.01 126% 0 0.2 6.8 56.0 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 0.9996, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9996` `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=0.9812` `prior_reliability=0.2` `competition=La Liga`	totalCross: 2.1035 -> 2.1256 fouls: 1.576 -> 1.5962
`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': 'Jonny Otto', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run'}`	-
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.008 -> 0.0144 expected_assists: 0.1437 -> 0.2311
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0143` `goal_rate=0.0` `scorer_weight=0.0124`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=1` `assist_probability=0.2063` `assist_rate=0.0016` `provider_weight=0.1849`	-

Juan Iglesias D 88 0 0.11 0.03 208% 1 0.7 6.8 63.6 34 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 0.9990, quality 0.472)	`market_value_eur=5800000` `quality_factor=0.472` `boost_factor=0.999` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`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': 'Nahuel Tenaglia', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run'}`	-
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0583 -> 0.1051 expected_assists: 0.0915 -> 0.1471
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0998` `goal_rate=0.0689` `scorer_weight=0.1154`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.1368` `assist_rate=0.0049` `provider_weight=0.1177`	-

Marcão D 81 0 0.11 - n/a 1 0.0 6.8 - 5 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 0.9944, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9944` `reference_quality=0.505` `history_matches=13` `history_shrink=0.2778`	-
`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 Boyé', '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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0631 -> 0.1137
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1075` `goal_rate=0.0` `scorer_weight=0.091`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.0071` `assist_rate=0.0` `provider_weight=0.0065`	-

Lucien Agoumé M 88 0 0.09 0.02 312% 1 0.5 6.9 62.1 33 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 1.0034, quality 0.616)	`market_value_eur=18500000` `quality_factor=0.6161` `boost_factor=1.0034` `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=0.9829` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 0.4188 -> 0.435 wonTackle: 2.1139 -> 2.1293 totalCross: 0.1896 -> 0.2045 fouls: 1.7691 -> 1.7804 interceptionWon: 1.3372 -> 1.3455
`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 Ibáñez', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.529, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1597, 'skill_edge': 0.0846, 'height_edge': 0.024, 'attacker_skill': 0.648, 'defender_skill': 0.46, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pablo Ibáñez', 'market_value': 4099999, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.46}], 'xg_override': 0.0514}	aerialWon: 0.4307 -> 1.2 totalShots: 0.6289 -> 0.7293 shotOffTarget: 0.4539 -> 0.5264 onTargetScoringAttempt: 0.1723 -> 0.1998 expectedGoalsOnTarget: 0.069 -> 0.08 goals: 0.0503 -> 0.0583 expectedGoals: 0.0443 -> 0.0514
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0514 -> 0.0926 expected_assists: 0.0433 -> 0.0696
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0884` `goal_rate=0.0583` `scorer_weight=0.0989`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.0672` `assist_rate=0.0494` `provider_weight=0.0742`	-

Youssouf Fofana M 86 1 0.28 0.09 217% 2 1.1 6.9 50.6 10 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 1.0110, quality 0.593)	`market_value_eur=16300000` `quality_factor=0.5932` `boost_factor=1.011` `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=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Antonio Blanco', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.488, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0997, 'skill_edge': 0.0318, 'height_edge': 0.036, 'attacker_skill': 0.6022, 'defender_skill': 0.5316, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Antonio Blanco', 'market_value': 9700000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5316}], 'xg_override': 0.1545}	aerialWon: 0.8265 -> 1.2 totalShots: 1.5523 -> 1.7071 shotOffTarget: 1.0032 -> 1.1032 onTargetScoringAttempt: 0.5491 -> 0.6038 bigChanceMissed: 0.2555 -> 0.281 expectedGoalsOnTarget: 0.229 -> 0.2518 expectedGoals: 0.1405 -> 0.1545 goals: 0.1385 -> 0.1523
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1545 -> 0.2785 expected_assists: 0.1118 -> 0.1798
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 80.0)	`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=1` `goal_probability=0.2431` `goal_rate=0.1523` `scorer_weight=0.2755`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=1` `assist_probability=0.1646` `assist_rate=0.1651` `provider_weight=0.2247`	-

Peque Fernández M 63 0 0.19 0.07 192% 1 0.3 6.7 31.9 36 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 0.441)	`market_value_eur=3300000` `quality_factor=0.4412` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`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': 'Jonny Otto, Facundo Garcés', 'matchup_zone': 'LW vs RWB + CB', 'duel_win_rate': 0.242, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9143, 'skill_edge': 0.0017, 'height_edge': -0.06, 'attacker_skill': 0.4412, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Jonny Otto', 'market_value': 2100000, 'role': 'RWB', 'price_index': 0.7, 'adjusted_quality': 0.4374}, {'player': 'Facundo Garcés', 'market_value': 1300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.1067}	aerialWon: 0.4431 -> 0.8 totalShots: 1.3207 -> 1.2075 shotOffTarget: 0.8972 -> 0.8203 onTargetScoringAttempt: 0.4235 -> 0.3872 expectedGoals: 0.1167 -> 0.1067 goals: 0.1135 -> 0.1038 expectedGoalsOnTarget: 0.106 -> 0.0969
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1067 -> 0.1923 expected_assists: 0.0592 -> 0.0952
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1749` `goal_rate=0.1038` `scorer_weight=0.1887`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.0908` `assist_rate=0.0636` `provider_weight=0.099`	-

Jon Guridi M 72 0 0.16 0.06 187% 1 0.5 6.7 50.8 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 0.9975, quality 0.437)	`market_value_eur=1700000` `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 0.0106)	`blend_weight=0.0106` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.7959` `prior_reliability=0.1333` `competition=La Liga`	totalCross: 0.8116 -> 0.824 onTargetScoringAttempt: 0.2684 -> 0.2782
`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': 'Nahuel Tenaglia, Facundo Garcés', 'matchup_zone': 'RW vs LWB + CB', 'duel_win_rate': 0.266, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9495, 'skill_edge': -0.0044, 'height_edge': -0.03, 'attacker_skill': 0.4374, 'defender_skill': 0.4472, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Nahuel Tenaglia', 'market_value': 3200000, 'role': 'LWB', 'price_index': 0.7, 'adjusted_quality': 0.4569}, {'player': 'Facundo Garcés', 'market_value': 1300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.0894}	aerialWon: 1.1781 -> 1.0 totalShots: 0.8585 -> 0.8152 shotOffTarget: 0.5803 -> 0.551 onTargetScoringAttempt: 0.2782 -> 0.2642
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0894 -> 0.1611 expected_assists: 0.04 -> 0.0643
`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_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=0.1488` `goal_rate=0.0767` `scorer_weight=0.1464`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.0623` `assist_rate=0.0569` `provider_weight=0.0764`	-

Giorgi Kochorashvili M 78 0 0.09 0.01 609% 1 0.4 6.9 40.4 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 0.9930, quality 0.454)	`market_value_eur=4300000` `quality_factor=0.4535` `boost_factor=0.993` `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=0.8612` `prior_reliability=0.0267` `competition=La Liga`	totalCross: 1.8297 -> 1.8662 totalShots: 0.7241 -> 0.7524 fouls: 0.2789 -> 0.2937 wasFouled: 0.2789 -> 0.2937
`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 Ibáñez', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.409, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9843, 'skill_edge': 0.0013, 'height_edge': -0.012, 'attacker_skill': 0.4629, 'defender_skill': 0.46, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pablo Ibáñez', 'market_value': 4099999, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.46}], 'xg_override': 0.0474}	aerialWon: 0.7721 -> 0.9 totalShots: 0.7524 -> 0.7406 shotOffTarget: 0.5128 -> 0.5047
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0474 -> 0.0854 expected_assists: 0.0909 -> 0.1462
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 74.0)	`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=0.0819` `goal_rate=0.0697` `scorer_weight=0.105`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.136` `assist_rate=0.0843` `provider_weight=0.1394`	-

Miguel Sierra F 74 1 0.23 0.05 388% 2 1.0 6.9 42.9 26 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 0.9990, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.999` `reference_quality=0.505` `history_matches=12` `history_shrink=0.2941`	-
`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': 'Facundo Garcés, Ville Koski', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.19, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.985, 'skill_edge': 0.0178, 'height_edge': -0.028, 'attacker_skill': 0.4939, 'defender_skill': 0.4543, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Facundo Garcés', 'market_value': 1300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Ville Koski', 'market_value': 4300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4712}], 'xg_override': 0.1274}	totalShots: 1.8879 -> 1.8596 shotOffTarget: 1.3955 -> 1.3746 onTargetScoringAttempt: 0.4924 -> 0.485
`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 1.60 (squad xG sum 0.8900, xG scale 1.8022, xA scale 1.6080, team xA 1.28 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.604` `squad_xg_sum=0.89` `squad_xa_sum=0.798` `team_expected_assists=1.2832` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1274 -> 0.2296 expected_assists: 0.0982 -> 0.1579
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 65.0)	`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=1` `goal_probability=0.2051` `goal_rate=0.1911` `scorer_weight=0.287`	-
`integer_assist_projection`	Team scoreline allocation: 2 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=2` `assists_allocated=0` `assist_probability=0.1461` `assist_rate=0.0` `provider_weight=0.1263`	-

Team totals 2 1.60 13 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Fran González	G	4.4m	10.9%	Market-value substitute prior
José Ángel Carmona	D	13.9m	31.3%	Market-value substitute prior
Andrés Castrin	D	13.8m	31.1%	Market-value substitute prior
Manu Bueno	M	14.8m	69.2%	Market-value substitute prior
Nico Guillén	M	22.0m	49.9%	Market-value substitute prior
Lucas Stassin	F	25.9m	58.6%	Market-value substitute prior

Alavés — projected line vs season baseline (5-3-2)

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

Antonio Sivera G 90 0 0.00 - n/a 0.0 7.1 64.6 34 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 0.9990, quality 0.470)	`market_value_eur=5600000` `quality_factor=0.4695` `boost_factor=0.999` `reference_quality=0.505` `history_matches=49` `history_shrink=0.0926`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0120)	`blend_weight=0.012` `history_matches=49` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.8276 -> 2.8337
`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': 'Youssouf Fofana, Miguel Sierra', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.5624}`	-
`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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	shots_faced: 14.8 -> 15.2 expected_saves: 3.62 -> 3.72 high_pressure_saves: 1.25 -> 1.28
`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_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=1.4144`	-
`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=0.8284`	-

Nahuel Tenaglia D 88 0 0.07 0.04 71% 1 0.7 6.7 61.4 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 0.9981, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.9981` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0125)	`blend_weight=0.0125` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=0.9728` `prior_reliability=0.2` `competition=La Liga`	totalCross: 1.2754 -> 1.2676 totalShots: 0.7977 -> 0.8039 wasFouled: 1.4516 -> 1.4456 fouls: 0.8439 -> 0.8496 interceptionWon: 1.1915 -> 1.1969
`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': 'Jon Guridi', 'matchup_zone': 'RW vs LWB + 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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0491 -> 0.0748 expected_assists: 0.0299 -> 0.0477
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0721` `goal_rate=0.0498` `scorer_weight=0.0753`	-
`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=0.0466` `assist_rate=0.0` `provider_weight=0.0382`	-

Jonny Otto D 85 0 0.02 0.01 87% 0 0.2 6.7 52.1 33 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=2100000` `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': 'Peque Fernández', 'matchup_zone': 'LW vs RWB + 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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0123 -> 0.0187 expected_assists: 0.0234 -> 0.0374
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 84.0)	`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=0.0185` `goal_rate=0.0` `scorer_weight=0.015`	-
`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=0.0367` `assist_rate=0.0` `provider_weight=0.0299`	-

Ville Koski D 90 0 0.12 0.04 204% 0 0.2 6.8 40.4 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 0.9963, quality 0.454)	`market_value_eur=4300000` `quality_factor=0.4535` `boost_factor=0.9963` `reference_quality=0.505` `history_matches=16` `history_shrink=0.2381`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0299)	`blend_weight=0.0299` `history_matches=16` `season_overlap_discount=1.0` `per90_to_match_factor=0.9956` `prior_reliability=0.1933` `competition=La Liga`	fouls: 0.874 -> 0.8479 wonTackle: 0.7384 -> 0.7266 totalShots: 0.3912 -> 0.3795 wasFouled: 0.3816 -> 0.3702 onTargetScoringAttempt: 0.1977 -> 0.1918
`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': 'Miguel Sierra', '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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0782 -> 0.1192 expected_assists: 0.0108 -> 0.0172
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 68.0)	`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=0.1124` `goal_rate=0.0818` `scorer_weight=0.1225`	-
`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=0.0171` `assist_rate=0.0` `provider_weight=0.0141`	-

Facundo Garcés D 90 0 0.08 0.03 141% 0 0.4 6.8 37.3 7 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=1300000` `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=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Peque Fernández', 'matchup_zone': 'LW vs RWB + 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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0549 -> 0.0837 expected_assists: 0.0095 -> 0.0152
`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_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=0.0803` `goal_rate=0.0` `scorer_weight=0.067`	-
`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=0.0151` `assist_rate=0.0` `provider_weight=0.0128`	-

Nicolás Valentini D 81 0 0.05 0.01 256% 1 0.3 6.8 39.6 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 0.9917, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.9917` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0018)	`blend_weight=0.0018` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.8958` `prior_reliability=0.0067` `competition=La Liga`	fouls: 0.6879 -> 0.7029 totalShots: 0.592 -> 0.6042
`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': 'Miguel Sierra', '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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0329 -> 0.0502 expected_assists: 0.0194 -> 0.031
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.049` `goal_rate=0.0` `scorer_weight=0.0402`	-
`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=0.0305` `assist_rate=0.0` `provider_weight=0.0248`	-

Antonio Blanco M 82 0 0.06 0.03 81% 1 1.0 6.9 62.6 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 1.0004, quality 0.519)	`market_value_eur=9700000` `quality_factor=0.5189` `boost_factor=1.0004` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0127)	`blend_weight=0.0127` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=0.9126` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.1609 -> 1.1771 fouls: 1.49 -> 1.5059 totalCross: 0.9675 -> 0.9746 totalShots: 0.6995 -> 0.7062
`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': 'Lucien Agoumé', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.362, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.87, 'skill_edge': -0.0524, 'height_edge': -0.036, 'attacker_skill': 0.5316, 'defender_skill': 0.648, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Lucien Agoumé', 'market_value': 18500000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.648}], 'xg_override': 0.0405}	aerialWon: 0.4808 -> 0.9 totalShots: 0.7062 -> 0.6144 shotOffTarget: 0.4983 -> 0.4335 onTargetScoringAttempt: 0.1986 -> 0.1728 goals: 0.0537 -> 0.0467 expectedGoals: 0.0466 -> 0.0405
`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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0405 -> 0.0617 expected_assists: 0.0632 -> 0.1009
`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=0.0598` `goal_rate=0.0467` `scorer_weight=0.0659`	-
`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=0.096` `assist_rate=0.0656` `provider_weight=0.103`	-

Ángel Pérez M 81 0 0.18 0.07 138% 2 1.0 6.9 62.6 33 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 0.9977, quality 0.457)	`market_value_eur=4600000` `quality_factor=0.4572` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0168)	`blend_weight=0.0168` `history_matches=26` `season_overlap_discount=1.0` `per90_to_match_factor=0.9007` `prior_reliability=0.16` `competition=La Liga`	wasFouled: 1.2343 -> 1.2199 totalCross: 3.714 -> 3.7021 interceptionWon: 0.7554 -> 0.7616 fouls: 1.086 -> 1.0804 wonTackle: 0.7038 -> 0.6983
`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': 'Lucien Agoumé', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.359, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8662, 'skill_edge': -0.083, 'height_edge': -0.008, 'attacker_skill': 0.4635, 'defender_skill': 0.648, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Lucien Agoumé', 'market_value': 18500000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.648}], 'xg_override': 0.1162}	aerialWon: 0.1879 -> 1.1 totalShots: 1.6164 -> 1.4001 shotOffTarget: 1.0322 -> 0.8941 onTargetScoringAttempt: 0.5823 -> 0.5044 goals: 0.1421 -> 0.1231 expectedGoals: 0.1342 -> 0.1162 expectedGoalsOnTarget: 0.1175 -> 0.1018 bigChanceMissed: 0.0987 -> 0.0855
`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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1162 -> 0.1771 expected_assists: 0.148 -> 0.2361
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 72.0)	`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=0.1623` `goal_rate=0.1231` `scorer_weight=0.1844`	-
`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=0.2103` `assist_rate=0.1463` `provider_weight=0.2341`	-

Pablo Ibáñez M 83 0 0.10 0.08 ok 1 1.2 6.8 63.6 33 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 0.451)	`market_value_eur=4099999` `quality_factor=0.4511` `boost_factor=0.9985` `reference_quality=0.505` `history_matches=48` `history_shrink=0.0943`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0123)	`blend_weight=0.0123` `history_matches=48` `season_overlap_discount=1.0` `per90_to_match_factor=0.9192` `prior_reliability=0.2` `competition=La Liga`	totalCross: 1.8608 -> 1.8455 wasFouled: 2.2061 -> 2.1978 wonTackle: 1.2609 -> 1.253 totalShots: 0.978 -> 0.9848
`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': 'Lucien Agoumé', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.311, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8403, 'skill_edge': -0.0846, 'height_edge': -0.024, 'attacker_skill': 0.46, 'defender_skill': 0.648, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Lucien Agoumé', 'market_value': 18500000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.648}], 'xg_override': 0.0624}	totalShots: 0.9848 -> 0.8275 shotOffTarget: 0.7306 -> 0.6139 aerialWon: 0.9386 -> 1.0 onTargetScoringAttempt: 0.2481 -> 0.2085 bigChanceMissed: 0.0967 -> 0.0813 expectedGoalsOnTarget: 0.082 -> 0.0689 expectedGoals: 0.0743 -> 0.0624 goals: 0.0644 -> 0.0541
`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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0624 -> 0.0951 expected_assists: 0.0707 -> 0.1129
`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=0.0907` `goal_rate=0.0541` `scorer_weight=0.0881`	-
`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=0.1068` `assist_rate=0.0704` `provider_weight=0.1126`	-

Lucas Boyé F 79 1 0.44 0.33 33% 2 2.1 6.8 61.8 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 0.9987, quality 0.466)	`market_value_eur=5300000` `quality_factor=0.4659` `boost_factor=0.9987` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0079)	`blend_weight=0.0079` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.8754` `prior_reliability=0.1067` `competition=La Liga`	wonTackle: 0.8388 -> 0.8538 totalShots: 2.0755 -> 2.081
`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': 'Kike Salas, Marcão', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9364, 'skill_edge': -0.0332, 'height_edge': -0.01, 'attacker_skill': 0.4659, 'defender_skill': 0.5397, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Kike Salas', 'market_value': 15400000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6363}, {'player': 'Marcão', 'market_value': 2600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4432}], 'xg_override': 0.2864}	totalShots: 2.081 -> 1.9486 shotOffTarget: 1.352 -> 1.266 onTargetScoringAttempt: 0.7266 -> 0.6804 expectedGoalsOnTarget: 0.3301 -> 0.3091 goals: 0.3185 -> 0.2982 expectedGoals: 0.3058 -> 0.2864 bigChanceMissed: 0.1547 -> 0.1449
`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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2864 -> 0.4367 expected_assists: 0.0484 -> 0.0773
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 77.0)	`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=1` `goal_probability=0.3538` `goal_rate=0.2982` `scorer_weight=0.452`	-
`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=0.0744` `assist_rate=0.005` `provider_weight=0.0618`	-

Abderrahman Rebbach F 74 0 0.13 0.04 204% 1 0.6 6.8 50.6 45 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=2400000` `quality_factor=0.4374` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`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': 'Kike Salas, Marcão', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8765, 'skill_edge': -0.046, 'height_edge': -0.038, 'attacker_skill': 0.4374, 'defender_skill': 0.5397, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Kike Salas', 'market_value': 15400000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6363}, {'player': 'Marcão', 'market_value': 2600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4432}], 'xg_override': 0.0856}	totalShots: 0.9633 -> 0.8444 shotOffTarget: 0.5768 -> 0.5056 onTargetScoringAttempt: 0.3865 -> 0.3388 bigChanceMissed: 0.1751 -> 0.1535 goals: 0.1366 -> 0.1197 expectedGoals: 0.0977 -> 0.0856
`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 1.38 (squad xG sum 0.9047, xG scale 1.5243, xA scale 1.5964, team xA 0.90 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.379` `squad_xg_sum=0.9047` `squad_xa_sum=0.5615` `team_expected_assists=0.8963` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0856 -> 0.1305 expected_assists: 0.0637 -> 0.1017
`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_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=0.1223` `goal_rate=0.1197` `scorer_weight=0.1631`	-
`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=0.0967` `assist_rate=0.0462` `provider_weight=0.086`	-

Team totals 1 1.38 10 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Grégoire Swiderski	G	4.4m	10.9%	Market-value substitute prior
Youssef Enriquez	D	13.7m	30.4%	Market-value substitute prior
Carlos Benavídez	D	17.1m	60.2%	Market-value substitute prior
Ander Guevara	M	10.4m	69.2%	Market-value substitute prior
Carles Aleñá	M	13.2m	69.2%	Market-value substitute prior
Toni Martínez	F	25.5m	33.8%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Lucien Agoumé vs Antonio Blanco will be the pivotal duel. Total antagonist xG — Home: 0.58, Away: 0.65. Home danger zone: CAM vs CM. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.8% / 49.2%, dominance ratio 0.54, key duel: Lucien Agoumé vs Antonio Blanco

Peque Fernández xG 0.11Jon Guridi xG 0.09Youssouf Fofana xG 0.15Lucas Boyé xG 0.29Abderrahman Rebbach xG 0.09Nahuel Tenaglia xG 0.05

Summary

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

Tactical parity between 4-2-3-1 and 5-3-2. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Lucien Agoumé vs Antonio Blanco will be the pivotal duel. Total antagonist xG — Home: 0.58, Away: 0.65. Home danger zone: CAM vs CM. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Everton vs Coventry

Premier League · 20261106 · 4-2-3-1 vs 4-2-3-1

Predicted 1-0Winner: EvertonWinning H 1-0 (10.9%)Winning A 0-1 (6.2%)Confidence 0.69λ home/away 1.77 / 1.01Most-likely P 10.9%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Everton vs Coventry. 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 1.681, Away 0.826). Final calibrated Poisson lambdas: Home 1.768, Away 1.013 (most likely score 1-0).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.68 / 0.83 Final λ (H/A) 1.77 / 1.01

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	Everton	Coventry
League position	14.00	16.00
Points per game	1.30	1.14
Attack index	0.89	0.84
Defense (concede) index	1.08	0.93
Form multiplier	1.01	0.99
Standing λ multiplier	0.99	0.91

Lambda decomposition (how the goal rates were built)

Stage	Everton λ	Coventry λ
Pre-competitive-floor	1.657	0.838
Pre-calibration (Micro-duels)	1.681	0.826
Final λ	1.768	1.013

competition calibration scale 1.115competition observed total goals 2.781quality gap applied Truemismatch score pressure applied Falsecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
1-1	11.2%
1-0	10.9%
2-1	9.8%
2-0	9.7%
0-0	6.3%

Home win	55.0%
Draw	23.5%
Away win	21.4%
Over 2.5	52.6%
BTTS yes	52.9%

Pregame fair line — favorite Everton (55.0%), fair total 2.78, fair spread 0.76

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.

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

Jordan Pickford G 90 0 0.00 - n/a 0.0 7.1 57.1 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 1.0018, quality 0.567)	`market_value_eur=13900000` `quality_factor=0.5671` `boost_factor=1.0018` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0085)	`blend_weight=0.0085` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	wasFouled: 0.2782 -> 0.2886 saves: 2.9521 -> 2.961
`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, Loum Tchaouna', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.8262}`	-
`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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	shots_faced: 7.8 -> 9.6 expected_saves: 1.9 -> 2.35 high_pressure_saves: 0.66 -> 0.81
`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=0.0` `scorer_weight=0.0` `squad_weight_total=1.8025`	-
`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=1.0979`	-

Vitaliy Mykolenko D 88 0 0.01 0.01 ok 0 0.2 6.7 52.1 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 1.0060, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.006` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0096)	`blend_weight=0.0096` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9741` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.2722 -> 1.26 totalCross: 2.2029 -> 2.1958 interceptionWon: 1.0675 -> 1.0619
`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': 'Right Wing vs Left 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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0564 -> 0.0964
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0089` `goal_rate=0.0` `scorer_weight=0.008`	-
`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=0.0919` `assist_rate=0.0068` `provider_weight=0.0771`	-

James Tarkowski D 90 0 0.05 0.06 ok 1 0.6 7.1 58.9 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 0.9988, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.9988` `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`	interceptionWon: 1.369 -> 1.3831 wasFouled: 1.6721 -> 1.6793
`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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0324 -> 0.0504 expected_assists: 0.0368 -> 0.0629
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0492` `goal_rate=0.1091` `scorer_weight=0.063`	-
`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=0.061` `assist_rate=0.1425` `provider_weight=0.0786`	-

Jarrad Branthwaite D 90 0 0.06 0.03 128% 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: 1.2311 -> 1.2363
`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': 'Loum Tchaouna', '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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.041 -> 0.0638 expected_assists: 0.0097 -> 0.0166
`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=0.0618` `goal_rate=0.0368` `scorer_weight=0.0609`	-
`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=0.0165` `assist_rate=0.0` `provider_weight=0.0139`	-

Michael Keane D 90 0 0.11 0.04 151% 1 0.5 6.8 37.2 29 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 0.9974, quality 0.437)	`market_value_eur=2800000` `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': 'Loum Tchaouna', '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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0682 -> 0.1061 expected_assists: 0.0388 -> 0.0663
`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=0.1007` `goal_rate=0.0359` `scorer_weight=0.0849`	-
`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=0.0641` `assist_rate=0.1089` `provider_weight=0.0829`	-

Kiernan Dewsbury-Hall M 88 0 0.29 0.14 109% 2 1.4 7.2 57.2 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 1.0101, quality 0.800)	`market_value_eur=44000000` `quality_factor=0.8002` `boost_factor=1.0101` `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=0.983` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.6698 -> 0.6777 totalCross: 3.6665 -> 3.674
`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': 0.52, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0589, 'skill_edge': 0.028, 'height_edge': 0.012, 'attacker_skill': 0.8002, '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': 0.188}	aerialWon: 0.4462 -> 1.0 totalShots: 1.9901 -> 2.1073 shotOffTarget: 1.3167 -> 1.3943 onTargetScoringAttempt: 0.6719 -> 0.7115 bigChanceMissed: 0.2224 -> 0.2355 goals: 0.1967 -> 0.2083 expectedGoals: 0.1775 -> 0.188 expectedGoalsOnTarget: 0.1758 -> 0.1862
`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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.188 -> 0.2925 expected_assists: 0.1612 -> 0.2751
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 81.0)	`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=0.2536` `goal_rate=0.2083` `scorer_weight=0.3175`	-
`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=0.2405` `assist_rate=0.1345` `provider_weight=0.2403`	-

Merlin Röhl M 85 0 0.09 0.01 782% 1 0.2 6.8 32.0 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 1.0063, quality 0.615)	`market_value_eur=18400000` `quality_factor=0.615` `boost_factor=1.0063` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0158)	`blend_weight=0.0158` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.9424` `prior_reliability=0.1267` `competition=Premier League`	wonTackle: 0.9012 -> 0.9184 totalCross: 1.7056 -> 1.7179 totalShots: 0.7489 -> 0.737 fouls: 1.1545 -> 1.1441 interceptionWon: 1.0205 -> 1.0122 wasFouled: 1.0028 -> 0.9948
`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': 'Jay DaSilva', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.549, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1008, 'skill_edge': 0.0085, 'height_edge': 0.06, 'attacker_skill': 0.615, 'defender_skill': 0.5961, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Jay DaSilva', 'market_value': 11600000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.5961}], 'xg_override': 0.0546}	totalShots: 0.7458 -> 0.821 shotOffTarget: 0.5515 -> 0.6071 onTargetScoringAttempt: 0.1943 -> 0.2139 expectedGoals: 0.0496 -> 0.0546
`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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0546 -> 0.085 expected_assists: 0.0543 -> 0.0928
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0815` `goal_rate=0.0498` `scorer_weight=0.0811`	-
`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=0.0886` `assist_rate=0.0612` `provider_weight=0.0989`	-

James Garner M 87 0 0.11 0.03 280% 1 0.6 7.2 58.8 33 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 1.0097, quality 0.834)	`market_value_eur=53000000` `quality_factor=0.834` `boost_factor=1.0097` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0034)	`blend_weight=0.0034` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=0.972` `prior_reliability=0.0533` `competition=Premier League`	wonTackle: 1.4272 -> 1.4389
`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': 'Caleb Yirenkyi', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.493, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.1078, 'skill_edge': 0.0734, 'height_edge': 0.0, 'attacker_skill': 0.8576, 'defender_skill': 0.6946, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Caleb Yirenkyi', 'market_value': 23000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.6946}], 'xg_override': 0.0684}	aerialWon: 0.3361 -> 1.1 totalShots: 0.8689 -> 0.9626 shotOffTarget: 0.587 -> 0.6503 onTargetScoringAttempt: 0.2819 -> 0.3123 goals: 0.0637 -> 0.0706 expectedGoals: 0.0617 -> 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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0684 -> 0.1064 expected_assists: 0.1222 -> 0.2088
`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` `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=0.1009` `goal_rate=0.0706` `scorer_weight=0.1084`	-
`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=0.1884` `assist_rate=0.0815` `provider_weight=0.167`	-

Harrison Armstrong M 85 0 0.13 0.04 230% 1 0.4 6.8 41.2 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 1.0127, quality 0.725)	`market_value_eur=31000000` `quality_factor=0.7249` `boost_factor=1.0127` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0158)	`blend_weight=0.0158` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.9396` `prior_reliability=0.1267` `competition=Premier League`	fouls: 0.9541 -> 0.9781 interceptionWon: 0.7179 -> 0.7379 totalShots: 0.9722 -> 0.9568 wonTackle: 0.9569 -> 0.9652 goalAssist: 0.0687 -> 0.0754
`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': 'Caleb Yirenkyi', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.462, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0615, 'skill_edge': 0.0299, 'height_edge': 0.012, 'attacker_skill': 0.761, 'defender_skill': 0.6946, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Caleb Yirenkyi', 'market_value': 23000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.6946}], 'xg_override': 0.0853}	aerialWon: 0.5232 -> 1.2 totalShots: 0.9674 -> 1.0269 shotOffTarget: 0.6722 -> 0.7135 bigChanceMissed: 0.3388 -> 0.3596 onTargetScoringAttempt: 0.2952 -> 0.3134
`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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0853 -> 0.1327 expected_assists: 0.0778 -> 0.1329
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 73.0)	`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=0.1243` `goal_rate=0.0735` `scorer_weight=0.1211`	-
`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=0.1244` `assist_rate=0.0754` `provider_weight=0.1304`	-

Christian Nørgaard M 72 0 0.07 0.00 4571% 1 0.0 6.7 15.4 21 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 0.9948, quality 0.460)	`market_value_eur=4800000` `quality_factor=0.4597` `boost_factor=0.9948` `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=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Caleb Yirenkyi, Frank Onyeka', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.187, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.922, 'skill_edge': -0.0631, 'height_edge': 0.01, 'attacker_skill': 0.4628, 'defender_skill': 0.603, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Caleb Yirenkyi', 'market_value': 23000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.6946}, {'player': 'Frank Onyeka', 'market_value': 7700000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.5113}], 'xg_override': 0.0446}	aerialWon: 0.1547 -> 1.2 totalShots: 0.7011 -> 0.6464 shotOffTarget: 0.5157 -> 0.4755 onTargetScoringAttempt: 0.1854 -> 0.1709
`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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0446 -> 0.0694 expected_assists: 0.0255 -> 0.0436
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 79.0)	`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=0.067` `goal_rate=0.0592` `scorer_weight=0.0801`	-
`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=0.0427` `assist_rate=0.047` `provider_weight=0.0545`	-

Thierno Barry F 85 1 0.69 0.30 129% 3 1.4 6.8 55.2 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 1.0074, quality 0.758)	`market_value_eur=36000000` `quality_factor=0.7581` `boost_factor=1.0074` `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=0.9466` `prior_reliability=0.1067` `competition=Premier League`	fouls: 0.8993 -> 0.8932
`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': 0.303, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.151, 'skill_edge': 0.0827, 'height_edge': 0.02, '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': 0.4401}	totalShots: 2.3929 -> 2.7543 shotOffTarget: 1.3236 -> 1.5235 bigChanceMissed: 1.3147 -> 1.5132 onTargetScoringAttempt: 1.0693 -> 1.2308 expectedGoalsOnTarget: 0.4298 -> 0.4947 goals: 0.3944 -> 0.454 expectedGoals: 0.3824 -> 0.4401
`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 1.77 (squad xG sum 1.1362, xG scale 1.5561, xA scale 1.7084, team xA 1.15 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.768` `squad_xg_sum=1.1362` `squad_xa_sum=0.6727` `team_expected_assists=1.1492` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.4401 -> 0.685 expected_assists: 0.0303 -> 0.0518
`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=1` `goal_probability=0.4959` `goal_rate=0.454` `scorer_weight=0.7045`	-
`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=0.0505` `assist_rate=0.0` `provider_weight=0.0414`	-

Team totals 1 1.77 15 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
Ainsley Maitland-Niles	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	21.7m	74.0%	Market-value substitute prior

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

Carl Rushworth G 90 0 0.00 - n/a 0.0 6.9 41.8 14 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 1.0145, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0145` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0309)	`blend_weight=0.0309` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.7913 -> 2.7513
`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': 1.6806}`	-
`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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	shots_faced: 16.0 -> 16.8 expected_saves: 3.92 -> 4.11 high_pressure_saves: 1.34 -> 1.41
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 76.0)	`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=1.0248`	-
`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=0.8008`	-

Jay DaSilva D 90 0 0.06 0.05 ok 0 0.3 6.7 47.7 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 1.0039, quality 0.541)	`market_value_eur=11600000` `quality_factor=0.5411` `boost_factor=1.0039` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0309)	`blend_weight=0.0309` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9967` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 0.9144 -> 0.9015 fouls: 0.8403 -> 0.8297 onTargetScoringAttempt: 0.1651 -> 0.1754
`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': 'Right Wing vs Left 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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0442 -> 0.0595 expected_assists: 0.0747 -> 0.0877
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 73.0)	`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=0.0578` `goal_rate=0.0991` `scorer_weight=0.0744`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.084` `assist_rate=0.1167` `provider_weight=0.1096`	-

Ethan Pinnock D 89 0 0.02 0.01 308% 1 0.1 6.8 18.3 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 0.9940, quality 0.437)	`market_value_eur=2800000` `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 0.0013)	`blend_weight=0.0013` `history_matches=12` `season_overlap_discount=1.0` `per90_to_match_factor=0.984` `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': '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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0166 -> 0.0223
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0221` `goal_rate=0.0` `scorer_weight=0.0178`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.02` `assist_rate=0.0` `provider_weight=0.0162`	-

Milan van Ewijk D 90 0 0.00 0.00 276% 0 0.1 6.8 42.5 16 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 1.0178, 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 0.0333)	`blend_weight=0.0333` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.2492 -> 1.2242 wasFouled: 0.678 -> 0.6554 interceptionWon: 1.1454 -> 1.1239 fouls: 0.4497 -> 0.468 totalShots: 0.3854 -> 0.3726 totalCross: 1.7758 -> 1.7666
`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 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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0568 -> 0.0666
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0031` `goal_rate=0.0` `scorer_weight=0.003`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0644` `assist_rate=0.0` `provider_weight=0.0533`	-

Bobby Thomas D 84 0 0.10 0.05 109% 1 1.1 6.9 44.6 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 1.0157, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0157` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0317)	`blend_weight=0.0317` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.9368` `prior_reliability=0.1267` `competition=Premier League`	wasFouled: 0.7442 -> 0.7831 interceptionWon: 1.0585 -> 1.025 fouls: 0.6292 -> 0.6561 totalShots: 0.9479 -> 0.9339 totalCross: 0.079 -> 0.0921 wonTackle: 0.6513 -> 0.6463
`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 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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0718 -> 0.0967 expected_assists: 0.0416 -> 0.0488
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0922` `goal_rate=0.0` `scorer_weight=0.0774`	-
`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`	-

Jack Rudoni M 83 0 0.29 0.17 77% 2 1.1 6.9 50.6 17 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 1.0145, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0145` `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': 'James Tarkowski', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.547, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0985, 'skill_edge': 0.067, 'height_edge': 0.0, 'attacker_skill': 0.6408, 'defender_skill': 0.4918, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'James Tarkowski', 'market_value': 5200000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4918}], 'xg_override': 0.2172}	totalShots: 1.8771 -> 2.062 aerialWon: 1.0748 -> 1.2 shotOffTarget: 1.2107 -> 1.33 onTargetScoringAttempt: 0.6664 -> 0.732 expectedGoalsOnTarget: 0.3075 -> 0.3378 bigChanceMissed: 0.2018 -> 0.2217 expectedGoals: 0.1977 -> 0.2172 goals: 0.1869 -> 0.2053
`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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2172 -> 0.2925 expected_assists: 0.146 -> 0.1714
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 75.0)	`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=0.2536` `goal_rate=0.2053` `scorer_weight=0.2795`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1575` `assist_rate=0.0944` `provider_weight=0.1371`	-

Caleb Yirenkyi M 77 0 0.07 0.01 511% 1 0.1 6.7 41.6 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 1.0166, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0166` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0232)	`blend_weight=0.0232` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8602` `prior_reliability=0.1` `competition=Premier League`	fouls: 2.6541 -> 2.6324 interceptionWon: 0.8151 -> 0.7962 totalCross: 0.2167 -> 0.225 wonTackle: 0.2757 -> 0.2693
`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': 'James Garner', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.347, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8922, 'skill_edge': -0.0734, 'height_edge': 0.0, 'attacker_skill': 0.6946, 'defender_skill': 0.8576, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'James Garner', 'market_value': 53000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8576}], 'xg_override': 0.0498}	aerialWon: 1.3117 -> 1.1 totalShots: 0.6244 -> 0.5571 shotOffTarget: 0.4558 -> 0.4067 onTargetScoringAttempt: 0.1653 -> 0.1475 goals: 0.0595 -> 0.0531 expectedGoals: 0.0558 -> 0.0498
`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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0498 -> 0.067 expected_assists: 0.0314 -> 0.0368
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 73.0)	`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=0.0648` `goal_rate=0.0531` `scorer_weight=0.0692`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0361` `assist_rate=0.0575` `provider_weight=0.046`	-

Matt Grimes M 88 0 0.04 0.01 236% 0 0.4 6.9 43.9 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 0.9957, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.9957` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0309)	`blend_weight=0.0309` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9761` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 2.0685 -> 2.1555 fouls: 0.7794 -> 0.7553 wonTackle: 0.6089 -> 0.5901 wasFouled: 0.4721 -> 0.4877 interceptionWon: 0.3917 -> 0.3796
`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', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.337, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.7896, 'skill_edge': -0.1351, 'height_edge': -0.008, 'attacker_skill': 0.4646, 'defender_skill': 0.765, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Vitaliy Mykolenko', 'market_value': 26000000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.765}], 'xg_override': 0.0285}	aerialWon: 0.7312 -> 1.0 totalShots: 0.5285 -> 0.4173 shotOffTarget: 0.3981 -> 0.3143 onTargetScoringAttempt: 0.1276 -> 0.1008 goals: 0.0561 -> 0.0443 expectedGoals: 0.0361 -> 0.0285
`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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0285 -> 0.0384 expected_assists: 0.0613 -> 0.0719
`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=0.0377` `goal_rate=0.0443` `scorer_weight=0.0461`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0694` `assist_rate=0.0643` `provider_weight=0.0738`	-

Frank Onyeka M 82 0 0.04 0.01 714% 1 0.2 6.7 38.7 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 0.9992, quality 0.495)	`market_value_eur=7700000` `quality_factor=0.4951` `boost_factor=0.9992` `reference_quality=0.505` `history_matches=13` `history_shrink=0.2778`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0120)	`blend_weight=0.012` `history_matches=13` `season_overlap_discount=1.0` `per90_to_match_factor=0.9062` `prior_reliability=0.0667` `competition=Premier League`	interceptionWon: 1.4713 -> 1.4863 fouls: 1.6509 -> 1.6638 totalShots: 0.7771 -> 0.7677 wasFouled: 1.5722 -> 1.5642
`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': 'James Garner', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.268, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7768, 'skill_edge': -0.1558, 'height_edge': 0.004, 'attacker_skill': 0.5113, 'defender_skill': 0.8576, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'James Garner', 'market_value': 53000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8576}], 'xg_override': 0.032}	aerialWon: 0.7596 -> 1.1 totalShots: 0.7746 -> 0.6017 shotOffTarget: 0.5717 -> 0.4441 onTargetScoringAttempt: 0.2029 -> 0.1576 expectedGoalsOnTarget: 0.0607 -> 0.0472 goals: 0.0567 -> 0.044 expectedGoals: 0.0412 -> 0.032
`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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.032 -> 0.0431 expected_assists: 0.0458 -> 0.0537
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 75.0)	`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=0.0422` `goal_rate=0.044` `scorer_weight=0.0494`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0523` `assist_rate=0.0506` `provider_weight=0.0564`	-

Victor Torp M 85 0 0.05 0.00 2229% 1 0.1 6.8 23.9 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 1.0103, quality 0.574)	`market_value_eur=14500000` `quality_factor=0.5737` `boost_factor=1.0103` `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=0.9444` `prior_reliability=0.0333` `competition=Premier League`	totalCross: 1.3198 -> 1.3873 interceptionWon: 0.1423 -> 0.1612 fouls: 0.4397 -> 0.4554 totalShots: 0.6403 -> 0.6334
`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': 'James Garner, Harrison Armstrong', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8173, 'skill_edge': -0.1023, 'height_edge': -0.022, 'attacker_skill': 0.582, 'defender_skill': 0.8093, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'James Garner', 'market_value': 53000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8576}, {'player': 'Harrison Armstrong', 'market_value': 31000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.761}], 'xg_override': 0.0404}	aerialWon: 0.2724 -> 1.0 totalShots: 0.6382 -> 0.5216 shotOffTarget: 0.4479 -> 0.3661 onTargetScoringAttempt: 0.1903 -> 0.1555 goals: 0.0662 -> 0.0541 expectedGoals: 0.0494 -> 0.0404
`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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0404 -> 0.0544 expected_assists: 0.0924 -> 0.1084
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 73.0)	`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=0.0529` `goal_rate=0.0541` `scorer_weight=0.0626`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1027` `assist_rate=0.0902` `provider_weight=0.1067`	-

Loum Tchaouna F 75 0 0.16 0.02 633% 1 0.5 6.8 35.6 37 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 1.0047, quality 0.623)	`market_value_eur=19200000` `quality_factor=0.6231` `boost_factor=1.0047` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0086)	`blend_weight=0.0086` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.8294` `prior_reliability=0.1` `competition=Premier League`	totalCross: 2.7656 -> 2.7751
`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': 'Michael Keane, Jarrad Branthwaite', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.9139, 'skill_edge': -0.0126, 'height_edge': -0.046, 'attacker_skill': 0.6231, 'defender_skill': 0.651, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Michael Keane', 'market_value': 2800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4465}, {'player': 'Jarrad Branthwaite', 'market_value': 46000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8555}], 'xg_override': 0.1213}	totalShots: 1.3797 -> 1.2609 shotOffTarget: 0.9126 -> 0.834 onTargetScoringAttempt: 0.4611 -> 0.4214 goals: 0.1532 -> 0.14 expectedGoals: 0.1327 -> 0.1213 bigChanceMissed: 0.063 -> 0.0576
`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 1.01 (squad xG sum 0.7524, xG scale 1.3463, xA scale 1.1734, team xA 0.81 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.013` `squad_xg_sum=0.7524` `squad_xa_sum=0.6907` `team_expected_assists=0.8104` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1213 -> 0.1633 expected_assists: 0.0773 -> 0.0907
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1507` `goal_rate=0.14` `scorer_weight=0.1811`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0867` `assist_rate=0.1167` `provider_weight=0.1134`	-

Team totals 0 1.01 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
Joel Latibeaudiere	D	13.6m	29.9%	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
Ephron Mason-Clark	F	25.9m	34.7%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — James Garner vs Caleb Yirenkyi will be the pivotal duel. Total antagonist xG — Home: 0.88, Away: 0.49. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Midfield — possession 51.1% / 48.9%, dominance ratio 0.54, key duel: James Garner vs Caleb Yirenkyi

Kiernan Dewsbury-Hall xG 0.19Merlin Röhl xG 0.05Christian Nørgaard xG 0.04Jack Rudoni xG 0.22Matt Grimes xG 0.03Victor Torp xG 0.04

Summary

Antagonist matchup analysis for Everton vs Coventry. Most likely scoreline: 1-0. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Everton 2W-4D-4L vs Coventry 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 — James Garner vs Caleb Yirenkyi will be the pivotal duel. Total antagonist xG — Home: 0.88, Away: 0.49. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Generated 2026-11-03 14:38:26 UTC · Soccer prediction reporting