Soccer predictions: actual data vs predicted data

Slate 20261107 · 8 match(es)

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

All matches overview

Match	Score	Winner	H / D / A	O2.5	BTTS	Conf	λ H/A	Actual	Result
Osasuna vs Athletic Club LaLiga	2-1	Osasuna	45.1% / 24.2% / 30.7%	57.3%	59.6%	0.67	1.66 / 1.33	-	pending
Espanyol vs Deportivo LaLiga	2-1	Espanyol	54.1% / 22.8% / 23.0%	57.3%	57.2%	0.69	1.85 / 1.13	-	pending
Arsenal vs Hull Premier League	1-0	Arsenal	64.4% / 20.9% / 14.7%	53.0%	48.3%	0.72	1.98 / 0.82	-	pending
Forest vs Man City Premier League	0-1	Man City	22.6% / 23.4% / 54.0%	54.2%	54.6%	0.69	1.07 / 1.78	-	pending
Fulham vs Newcastle Premier League	1-0	Fulham	42.9% / 25.4% / 31.8%	52.6%	56.1%	0.66	1.51 / 1.27	-	pending
Valencia vs Real Madrid LaLiga	0-2	Real Madrid	14.2% / 18.7% / 67.2%	61.8%	54.4%	0.73	0.94 / 2.26	-	pending
Málaga vs Racing Club LaLiga	1-0	Málaga	42.8% / 26.1% / 31.1%	49.5%	53.6%	0.65	1.45 / 1.20	-	pending
Leeds vs Tottenham Premier League	1-1	Draw	40.2% / 25.6% / 34.3%	52.6%	56.4%	0.65	1.46 / 1.33	-	pending

Match detail

Osasuna vs Athletic Club

LaLiga · 20261107 · 4-3-3 vs 4-2-3-1

Predicted 2-1Winner: OsasunaWinning H 2-1 (9.2%)Winning A 1-2 (7.4%)Confidence 0.67λ home/away 1.66 / 1.33Most-likely P 9.2%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Osasuna vs Athletic Club. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-3-3 vs 4-2-3-1 (duel lambdas: Home 1.117, Away 1.080). Final calibrated Poisson lambdas: Home 1.656, Away 1.328 (most likely score 2-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.12 / 1.08 Final λ (H/A) 1.66 / 1.33

FBref Team Priors: Osasuna (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.741) vs Athletic Club (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.741) | 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	Osasuna	Athletic Club
League position	14.00	7.00
Points per game	1.20	1.35
Attack index	0.85	0.91
Defense (concede) index	0.82	1.15
Form multiplier	0.99	1.01
Standing λ multiplier	0.86	1.02

Lambda decomposition (how the goal rates were built)

Stage	Osasuna λ	Athletic Club λ
FBref Squad Prior E[λ] (weight 0.228)	0.741	0.741
Pre-competitive-floor	1.220	1.055
Pre-calibration (Micro-duels)	1.117	1.080
Final λ	1.656	1.328

competition calibration scale 1.312competition 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	11.2%
2-1	9.2%
1-0	8.3%
1-2	7.4%
2-0	6.9%

Home win	45.1%
Draw	24.2%
Away win	30.7%
Over 2.5	57.3%
BTTS yes	59.6%

Pregame fair line — favorite Osasuna (45.1%), fair total 2.98, fair spread 0.33

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.

Osasuna — projected line vs season baseline (4-3-3)

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

Sergio Herrera G 88 0 0.00 - n/a 0.0 7.0 52.0 32 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0138)	`blend_weight=0.0138` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.977` `prior_reliability=0.2` `competition=La Liga`	saves: 2.678 -> 2.6545 wasFouled: 0.2569 -> 0.2624
`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': 'Oihan Sancet, Robert Navarro', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.0798}`	-
`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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	shots_faced: 10.3 -> 12.6 expected_saves: 2.53 -> 3.08 high_pressure_saves: 0.86 -> 1.06
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 79.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=1.7367`	-
`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=1.0448`	-

Alejandro Catena D 90 0 0.15 0.05 197% 1 0.3 6.9 60.2 32 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9979, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`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': 'Robert Navarro', '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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1015 -> 0.1531 expected_assists: 0.0959 -> 0.1491
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 85.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_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=0.142` `goal_rate=0.0176` `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=0.1385` `assist_rate=0.1121` `provider_weight=0.1657`	-

Enzo Boyomo D 86 0 0.06 0.03 132% 0 0.4 6.8 43.6 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0026, quality 0.575)	`market_value_eur=14600000` `quality_factor=0.5748` `boost_factor=1.0026` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0033)	`blend_weight=0.0033` `history_matches=35` `season_overlap_discount=1.0` `per90_to_match_factor=0.9601` `prior_reliability=0.04` `competition=La Liga`	wonTackle: 0.823 -> 0.8307 fouls: 0.8518 -> 0.8594
`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': 'Peio Canales', 'matchup_zone': 'Right Wing vs Left Back — Flank 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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0428 -> 0.0645
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 79.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.0625` `goal_rate=0.0069` `scorer_weight=0.0516`	-
`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=0.0134` `assist_rate=0.0669` `provider_weight=0.0169`	-

Jorge Herrando D 72 0 0.04 0.01 392% 0 0.1 6.8 46.5 26 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9973, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0126)	`blend_weight=0.0126` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=0.7969` `prior_reliability=0.14` `competition=La Liga`	onTargetScoringAttempt: 0.2249 -> 0.2318 totalShots: 0.3327 -> 0.3383
`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': 'Robert Navarro', '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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0253 -> 0.0382 expected_assists: 0.026 -> 0.0404
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0375` `goal_rate=0.0` `scorer_weight=0.0306`	-
`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=0.0396` `assist_rate=0.0302` `provider_weight=0.0426`	-

Valentin Rosier D 85 0 0.04 0.02 99% 1 0.6 6.7 59.3 27 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 0.9974, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `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': 'Iñigo Ruiz de Galarreta', 'matchup_zone': 'Left Wing vs Right Back — Flank 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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0293 -> 0.0442 expected_assists: 0.0611 -> 0.095
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 78.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.0432` `goal_rate=0.0299` `scorer_weight=0.0445`	-
`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=0.0906` `assist_rate=0.0012` `provider_weight=0.076`	-

Jon Moncayola M 82 0 0.06 0.05 ok 1 0.5 6.8 60.8 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 0.9996, quality 0.490)	`market_value_eur=7300000` `quality_factor=0.4903` `boost_factor=0.9996` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0106)	`blend_weight=0.0106` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=0.9056` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.467 -> 2.4523 interceptionWon: 0.5678 -> 0.581 wonTackle: 0.8813 -> 0.8912
`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': 'Beñat Gerenabarrena', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.497, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0689, 'skill_edge': 0.0109, 'height_edge': 0.036, 'attacker_skill': 0.5, 'defender_skill': 0.4759, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Beñat Gerenabarrena', 'market_value': 5200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4759}], 'xg_override': 0.0405}	aerialWon: 0.4309 -> 1.1 totalShots: 0.5455 -> 0.5831 shotOffTarget: 0.3683 -> 0.3937 onTargetScoringAttempt: 0.1772 -> 0.1894
`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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0405 -> 0.0611 expected_assists: 0.0713 -> 0.1108
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 81.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0593` `goal_rate=0.0669` `scorer_weight=0.0764`	-
`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=0.1049` `assist_rate=0.0685` `provider_weight=0.1082`	-

Moi Gómez M 77 0 0.06 0.01 715% 0 0.2 7.1 45.6 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9973, quality 0.437)	`market_value_eur=1600000` `quality_factor=0.4374` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0114)	`blend_weight=0.0114` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.8591` `prior_reliability=0.1333` `competition=La Liga`	totalCross: 2.1195 -> 2.1002 interceptionWon: 0.648 -> 0.6553 wonTackle: 0.5733 -> 0.5668 totalShots: 0.5036 -> 0.4979
`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': 'Beñat Gerenabarrena', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.437, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9804, 'skill_edge': -0.0173, 'height_edge': 0.004, 'attacker_skill': 0.4374, 'defender_skill': 0.4759, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Beñat Gerenabarrena', 'market_value': 5200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4759}], 'xg_override': 0.039}	aerialWon: 0.4176 -> 0.9 totalShots: 0.502 -> 0.4922 shotOffTarget: 0.3657 -> 0.3585
`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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.039 -> 0.0588 expected_assists: 0.1159 -> 0.1803
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 76.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0571` `goal_rate=0.0604` `scorer_weight=0.0729`	-
`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=0.165` `assist_rate=0.1022` `provider_weight=0.1654`	-

Iker Muñoz M 81 0 0.07 0.01 415% 1 0.4 6.9 42.9 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 0.9968, quality 0.437)	`market_value_eur=1800000` `quality_factor=0.4374` `boost_factor=0.9968` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0156)	`blend_weight=0.0156` `history_matches=27` `season_overlap_discount=1.0` `per90_to_match_factor=0.8978` `prior_reliability=0.1533` `competition=La Liga`	wasFouled: 1.7395 -> 1.7246 totalCross: 0.5181 -> 0.5283
`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': 'Beñat Gerenabarrena', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.427, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0098, 'skill_edge': -0.0173, 'height_edge': 0.024, 'attacker_skill': 0.4374, 'defender_skill': 0.4759, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Beñat Gerenabarrena', 'market_value': 5200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4759}], 'xg_override': 0.0473}	aerialWon: 1.643 -> 1.0 totalShots: 0.611 -> 0.617
`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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0473 -> 0.0713 expected_assists: 0.0402 -> 0.0625
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 73.0)	`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=0.0688` `goal_rate=0.0494` `scorer_weight=0.0728`	-
`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=0.0606` `assist_rate=0.0556` `provider_weight=0.0732`	-

Ante Budimir F 87 1 0.55 0.48 ok 2 2.6 6.8 63.9 34 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 0.9981, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9981` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=0.9712` `prior_reliability=0.1467` `competition=La Liga`	totalShots: 2.4772 -> 2.4902 wasFouled: 1.2591 -> 1.2718 onTargetScoringAttempt: 0.9927 -> 1.0035 wonTackle: 0.5852 -> 0.592
`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': 'Aymeric Laporte, Dani Vivian', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9077, 'skill_edge': -0.0748, 'height_edge': 0.012, 'attacker_skill': 0.4374, 'defender_skill': 0.6037, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Aymeric Laporte', 'market_value': 8400000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5365}, {'player': 'Dani Vivian', 'market_value': 18200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6709}], 'xg_override': 0.3658}	totalShots: 2.4902 -> 2.2604 shotOffTarget: 1.4845 -> 1.3475 onTargetScoringAttempt: 1.0035 -> 0.9109 expectedGoalsOnTarget: 0.5953 -> 0.5404 bigChanceMissed: 0.528 -> 0.4793 goals: 0.4355 -> 0.3953 expectedGoals: 0.403 -> 0.3658
`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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3658 -> 0.5516 expected_assists: 0.0323 -> 0.0502
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 82.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.424` `goal_rate=0.3953` `scorer_weight=0.5907`	-
`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=0.049` `assist_rate=0.0` `provider_weight=0.0402`	-

Rubén García F 71 0 0.16 0.06 157% 1 0.9 6.9 58.1 42 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 0.9980, quality 0.437)	`market_value_eur=1700000` `quality_factor=0.4374` `boost_factor=0.998` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0074)	`blend_weight=0.0074` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.7902` `prior_reliability=0.1133` `competition=La Liga`	totalCross: 4.4939 -> 4.5019 totalShots: 1.1581 -> 1.1637
`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': 'Yeray Álvarez', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.432, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9294, 'skill_edge': 0.0, 'height_edge': -0.048, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Yeray Álvarez', 'market_value': 930000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.1091}	totalShots: 1.1637 -> 1.0815 shotOffTarget: 0.7404 -> 0.6881 onTargetScoringAttempt: 0.4217 -> 0.3919 goals: 0.1371 -> 0.1274 expectedGoals: 0.1174 -> 0.1091 bigChanceMissed: 0.1024 -> 0.0952
`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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1091 -> 0.1645 expected_assists: 0.0981 -> 0.1525
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 77.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1517` `goal_rate=0.1274` `scorer_weight=0.1834`	-
`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=0.1414` `assist_rate=0.1156` `provider_weight=0.1705`	-

Jonathan Dubasin F 70 1 0.27 0.13 103% 2 0.6 6.8 45.3 17 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 0.9949, quality 0.454)	`market_value_eur=4300000` `quality_factor=0.4535` `boost_factor=0.9949` `reference_quality=0.505` `history_matches=10` `history_shrink=0.3333`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0188)	`blend_weight=0.0188` `history_matches=10` `season_overlap_discount=1.0` `per90_to_match_factor=0.7748` `prior_reliability=0.0867` `competition=La Liga`	wonTackle: 0.9366 -> 0.919 interceptionWon: 0.8744 -> 0.8916 totalOffside: 0.5308 -> 0.5208 fouls: 0.7694 -> 0.7773 wasFouled: 0.2255 -> 0.2325
`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': 'Yuri Berchiche', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.483, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0048, 'skill_edge': 0.0073, 'height_edge': -0.004, 'attacker_skill': 0.4535, 'defender_skill': 0.4374, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Yuri Berchiche', 'market_value': 910000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.181}	totalShots: 1.4945 -> 1.5017
`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 1.66 (squad xG sum 1.0981, xG scale 1.5081, xA scale 1.5547, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.656` `squad_xg_sum=1.0981` `squad_xa_sum=0.6924` `team_expected_assists=1.0764` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.181 -> 0.273 expected_assists: 0.0804 -> 0.125
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 77.0)	`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2389` `goal_rate=0.2301` `scorer_weight=0.331`	-
`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=0.1175` `assist_rate=0.0` `provider_weight=0.1`	-

Team totals 2 1.66 11 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Aitor Fernández	G	4.4m	10.9%	Market-value substitute prior
Abel Bretones	D	13.6m	21.7%	Market-value substitute prior
Rockson Yeboah	D	13.6m	29.9%	Market-value substitute prior
Aimar Oroz	M	14.9m	43.9%	Market-value substitute prior
Lucas Torró	M	18.1m	56.4%	Market-value substitute prior
Romain Del Castillo	F	25.4m	56.2%	Market-value substitute prior

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

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

Unai Simón G 84 0 0.00 - n/a 0.0 7.0 58.5 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 1.0040, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.004` `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=0.9329` `prior_reliability=0.2` `competition=La Liga`	saves: 2.9989 -> 3.0082
`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': 'Ante Budimir, Jonathan Dubasin', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.1166}`	-
`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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	shots_faced: 10.6 -> 15.7 expected_saves: 2.59 -> 3.84 high_pressure_saves: 0.89 -> 1.32
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 85.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=1.4267`	-
`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=1.0061`	-

Yuri Berchiche D 78 0 0.07 0.02 183% 1 1.0 7.0 55.1 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=910000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0054)	`blend_weight=0.0054` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.8656` `prior_reliability=0.0733` `competition=La Liga`	totalShots: 1.2353 -> 1.2413 wonTackle: 1.0031 -> 0.9977 fouls: 0.656 -> 0.661
`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': 'Jonathan Dubasin', '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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0476 -> 0.0675 expected_assists: 0.1455 -> 0.1831
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 79.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0653` `goal_rate=0.0` `scorer_weight=0.054`	-
`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=0.1673` `assist_rate=0.1268` `provider_weight=0.1656`	-

Aymeric Laporte D 85 0 0.07 0.07 ok 1 0.5 7.0 53.8 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9999, quality 0.503)	`market_value_eur=8400000` `quality_factor=0.5035` `boost_factor=0.9999` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0137)	`blend_weight=0.0137` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.9497` `prior_reliability=0.16` `competition=La Liga`	fouls: 1.0724 -> 1.0631 wonTackle: 0.8242 -> 0.8292
`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': 'Ante Budimir', '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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0528 -> 0.0749
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 84.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0722` `goal_rate=0.0` `scorer_weight=0.0599`	-
`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=0.0177` `assist_rate=0.0031` `provider_weight=0.0148`	-

Yeray Álvarez D 81 0 0.06 0.02 222% 1 0.2 6.9 38.0 21 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=930000` `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 0.0255)	`blend_weight=0.0255` `history_matches=12` `season_overlap_discount=1.0` `per90_to_match_factor=0.9024` `prior_reliability=0.1333` `competition=La Liga`	totalCross: 0.8649 -> 0.8889 totalShots: 0.5928 -> 0.6122 wonTackle: 0.5787 -> 0.564 goalAssist: 0.0934 -> 0.1025 wasFouled: 0.6635 -> 0.6581
`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': 'Rubén García', '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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0396 -> 0.0562 expected_assists: 0.0297 -> 0.0374
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 77.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0546` `goal_rate=0.0` `scorer_weight=0.045`	-
`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=0.1025` `provider_weight=0.0467`	-

Dani Vivian D 79 0 0.03 0.02 84% 1 0.4 6.7 48.3 22 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0044, quality 0.613)	`market_value_eur=18200000` `quality_factor=0.613` `boost_factor=1.0044` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`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': 'Ante Budimir', '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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0239 -> 0.0339 expected_assists: 0.0281 -> 0.0354
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0333` `goal_rate=0.0578` `scorer_weight=0.0424`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0348` `assist_rate=0.0` `provider_weight=0.0283`	-

Iñigo Ruiz de Galarreta M 64 0 0.09 0.02 284% 1 0.6 7.1 58.5 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.437)	`market_value_eur=1800000` `quality_factor=0.4374` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0037)	`blend_weight=0.0037` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.7158` `prior_reliability=0.0533` `competition=La Liga`	fouls: 1.5193 -> 1.5269
`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': 'Valentin Rosier', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.468, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9824, 'skill_edge': -0.008, 'height_edge': -0.004, 'attacker_skill': 0.4374, 'defender_skill': 0.4551, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Valentin Rosier', 'market_value': 3100000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4551}], 'xg_override': 0.0639}	aerialWon: 0.9703 -> 0.9 totalShots: 0.8901 -> 0.8744 shotOffTarget: 0.6363 -> 0.6251
`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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0639 -> 0.0906 expected_assists: 0.1055 -> 0.1327
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 82.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0866` `goal_rate=0.0638` `scorer_weight=0.0905`	-
`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=0.1243` `assist_rate=0.1057` `provider_weight=0.1329`	-

Oihan Sancet M 81 1 0.42 0.26 61% 3 1.8 6.9 61.7 23 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 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0063` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0150)	`blend_weight=0.015` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.9019` `prior_reliability=0.18` `competition=La Liga`	totalShots: 2.0801 -> 2.0888 interceptionWon: 0.2163 -> 0.2231 fouls: 0.6682 -> 0.6632
`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': 'Iker Muñoz', 'matchup_zone': 'Attacking Mid vs Single Holding Mid — Space Creator Duel', 'duel_win_rate': 0.605, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2131, 'skill_edge': 0.109, 'height_edge': 0.036, 'attacker_skill': 0.6796, 'defender_skill': 0.4374, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Iker Muñoz', 'market_value': 1800000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.2992}	aerialWon: 0.7062 -> 1.2 totalShots: 2.0888 -> 2.5339 shotOffTarget: 1.3219 -> 1.6036 onTargetScoringAttempt: 0.7618 -> 0.9241 bigChanceMissed: 0.4451 -> 0.54 goals: 0.2962 -> 0.3593 expectedGoals: 0.2466 -> 0.2992 expectedGoalsOnTarget: 0.2451 -> 0.2973
`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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2992 -> 0.4244 expected_assists: 0.1399 -> 0.176
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 78.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3458` `goal_rate=0.3593` `scorer_weight=0.4974`	-
`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=0.1614` `assist_rate=0.1305` `provider_weight=0.1673`	-

Beñat Gerenabarrena M 79 0 0.04 0.00 1775% 0 0.1 6.8 35.7 13 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9950, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.995` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0379)	`blend_weight=0.0379` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.8832` `prior_reliability=0.14` `competition=La Liga`	totalCross: 0.9188 -> 0.9796 interceptionWon: 1.8932 -> 1.933 fouls: 2.2103 -> 2.2381 wonTackle: 1.6337 -> 1.6515 wasFouled: 1.4033 -> 1.4139 onTargetScoringAttempt: 0.1373 -> 0.1478
`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 Moncayola', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.353, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9311, 'skill_edge': -0.0109, 'height_edge': -0.036, 'attacker_skill': 0.4759, 'defender_skill': 0.5, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Jon Moncayola', 'market_value': 7300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5}], 'xg_override': 0.0317}	aerialWon: 0.6976 -> 0.9 totalShots: 0.4711 -> 0.4386 shotOffTarget: 0.3233 -> 0.301 onTargetScoringAttempt: 0.1478 -> 0.1376
`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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0317 -> 0.045 expected_assists: 0.0444 -> 0.0559
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 80.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.044` `goal_rate=0.0406` `scorer_weight=0.0499`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0544` `assist_rate=0.0595` `provider_weight=0.0648`	-

Mikel Jauregizar M 70 0 0.11 0.03 272% 1 0.7 6.8 55.6 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 1.0057, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0057` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0050)	`blend_weight=0.005` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.7826` `prior_reliability=0.0733` `competition=La Liga`	totalCross: 1.437 -> 1.4299 interceptionWon: 1.0022 -> 1.0078
`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 Moncayola', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.48, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1174, 'skill_edge': 0.0999, 'height_edge': -0.02, 'attacker_skill': 0.7219, 'defender_skill': 0.5, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Jon Moncayola', 'market_value': 7300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5}], 'xg_override': 0.0767}	aerialWon: 1.65 -> 1.0 totalShots: 0.9626 -> 1.0756 shotOffTarget: 0.6842 -> 0.7645 onTargetScoringAttempt: 0.2784 -> 0.3111 expectedGoals: 0.0686 -> 0.0767 goals: 0.0554 -> 0.0619 expectedGoalsOnTarget: 0.0481 -> 0.0537
`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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0767 -> 0.1088 expected_assists: 0.0531 -> 0.0668
`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_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=0.1031` `goal_rate=0.0619` `scorer_weight=0.0961`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0646` `assist_rate=0.0561` `provider_weight=0.0687`	-

Peio Canales M 80 0 0.09 0.04 130% 1 0.5 6.9 41.8 11 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0017, quality 0.519)	`market_value_eur=9700000` `quality_factor=0.5189` `boost_factor=1.0017` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0415)	`blend_weight=0.0415` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.8876` `prior_reliability=0.1533` `competition=La Liga`	onTargetScoringAttempt: 0.2253 -> 0.248 totalShots: 0.6943 -> 0.7137 fouls: 0.7746 -> 0.7585 wasFouled: 1.1607 -> 1.1766 wonTackle: 1.0358 -> 1.0248 totalCross: 1.3747 -> 1.3817
`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': 'Enzo Boyomo', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.402, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.885, 'skill_edge': -0.0542, 'height_edge': -0.024, 'attacker_skill': 0.5189, 'defender_skill': 0.6394, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Enzo Boyomo', 'market_value': 14600000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.6394}], 'xg_override': 0.0627}	aerialWon: 0.0 -> 0.9 totalShots: 0.717 -> 0.6346 shotOffTarget: 0.469 -> 0.4151 onTargetScoringAttempt: 0.248 -> 0.2195 goals: 0.0794 -> 0.0703 expectedGoals: 0.0708 -> 0.0627
`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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0627 -> 0.0889 expected_assists: 0.0789 -> 0.0993
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 73.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0851` `goal_rate=0.0703` `scorer_weight=0.0949`	-
`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=0.0945` `assist_rate=0.08` `provider_weight=0.1001`	-

Robert Navarro F 77 0 0.23 0.12 96% 2 0.8 7.0 52.0 41 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 0.9996, quality 0.493)	`market_value_eur=7500000` `quality_factor=0.4927` `boost_factor=0.9996` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Alejandro Catena, Jorge Herrando', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9407, 'skill_edge': 0.0196, 'height_edge': -0.06, 'attacker_skill': 0.4927, 'defender_skill': 0.449, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Alejandro Catena', 'market_value': 2700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4449}, {'player': 'Jorge Herrando', 'market_value': 3200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4531}], 'xg_override': 0.163}	totalShots: 1.5662 -> 1.4734 shotOffTarget: 0.96 -> 0.9031 onTargetScoringAttempt: 0.6062 -> 0.5703 expectedGoalsOnTarget: 0.2526 -> 0.2376 goals: 0.2151 -> 0.2023 expectedGoals: 0.1733 -> 0.163 bigChanceMissed: 0.1111 -> 0.1045
`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 1.33 (squad xG sum 0.9363, xG scale 1.4183, xA scale 1.2583, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.328` `squad_xg_sum=0.9363` `squad_xa_sum=0.8443` `team_expected_assists=1.0624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.163 -> 0.2312 expected_assists: 0.1444 -> 0.1817
`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=0.2064` `goal_rate=0.2023` `scorer_weight=0.2739`	-
`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=0.1661` `assist_rate=0.0` `provider_weight=0.1454`	-

Team totals 1 1.33 13 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Alex Padilla	G	4.4m	10.9%	Market-value substitute prior
Aitor Paredes	D	13.8m	22.1%	Market-value substitute prior
Jesús Areso	D	13.7m	21.9%	Market-value substitute prior
Beñat Prados	M	22.4m	51.9%	Market-value substitute prior
Alejandro Rego Mora	M	22.1m	50.4%	Market-value substitute prior
Nico Williams	F	25.8m	62.0%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~52% possession expected (Jon Moncayola vs Mikel Jauregizar). Total antagonist xG — Home: 0.78, Away: 0.70. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Attacking Mid vs Single Holding Mid — Space Creator Duel.

Midfield — possession 48.1% / 51.9%, dominance ratio 0.43, key duel: Jon Moncayola vs Mikel Jauregizar

Rubén García xG 0.11Jonathan Dubasin xG 0.18Ante Budimir xG 0.37Iñigo Ruiz de Galarreta xG 0.06Peio Canales xG 0.06Oihan Sancet xG 0.30

Summary

Antagonist matchup analysis for Osasuna vs Athletic Club. Most likely scoreline: 2-1. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Osasuna 3W-3D-4L vs Athletic Club over 10 meetings.

Tactical parity between 4-3-3 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~52% possession expected (Jon Moncayola vs Mikel Jauregizar). Total antagonist xG — Home: 0.78, Away: 0.70. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Attacking Mid vs Single Holding Mid — Space Creator Duel.

Espanyol vs Deportivo

LaLiga · 20261107 · 4-2-3-1 vs 4-2-3-1

Predicted 2-1Winner: EspanyolWinning H 2-1 (9.8%)Winning A 1-2 (6.0%)Confidence 0.69λ home/away 1.85 / 1.13Most-likely P 9.8%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Espanyol vs Deportivo. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 1.402, Away 0.851). Final calibrated Poisson lambdas: Home 1.851, Away 1.132 (most likely score 2-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (0 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.40 / 0.85 Final λ (H/A) 1.85 / 1.13

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	Espanyol	Deportivo
League position	13.00	12.00
Points per game	1.13	1.20
Attack index	0.94	0.94
Defense (concede) index	0.94	0.97
Form multiplier	1.00	1.00
Standing λ multiplier	0.95	0.96

Lambda decomposition (how the goal rates were built)

Stage	Espanyol λ	Deportivo λ
Pre-competitive-floor	1.422	0.839
Pre-calibration (Micro-duels)	1.403	0.851
Final λ	1.851	1.132

competition calibration scale 1.32competition observed total goals 2.984quality gap applied Falsemismatch score pressure applied Falsecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
1-1	10.7%
2-1	9.8%
1-0	9.3%
2-0	8.7%
3-1	6.1%

Home win	54.1%
Draw	22.8%
Away win	23.0%
Over 2.5	57.3%
BTTS yes	57.2%

Pregame fair line — favorite Espanyol (54.1%), fair total 2.98, fair spread 0.72

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.

Espanyol — 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

Marko Dmitrović G 90 0 0.00 - n/a 0.0 7.0 55.8 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 0.9979, quality 0.437)	`market_value_eur=650000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0133)	`blend_weight=0.0133` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.9989 -> 3.0166
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Bil Nsongo, Diego Villares', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.8507}`	-
`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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	shots_faced: 8.1 -> 10.8 expected_saves: 1.98 -> 2.65 high_pressure_saves: 0.68 -> 0.91
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 79.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=1.9266`	-
`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=1.316`	-

Leandro Cabrera D 90 0 0.14 0.06 116% 1 1.1 6.9 62.5 31 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 0.9980, quality 0.437)	`market_value_eur=930000` `quality_factor=0.4374` `boost_factor=0.998` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Bil Nsongo', '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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.0747 -> 0.1382 expected_assists: 0.0235 -> 0.0435
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 76.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1291` `goal_rate=0.1595` `scorer_weight=0.1727`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0426` `assist_rate=0.0` `provider_weight=0.0348`	-

Roger Hinojo D 75 0 0.01 0.00 190% 0 0.1 6.7 51.6 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 0.9934, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.9934` `reference_quality=0.505` `history_matches=10` `history_shrink=0.3333`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0433)	`blend_weight=0.0433` `history_matches=10` `season_overlap_discount=1.0` `per90_to_match_factor=0.8387` `prior_reliability=0.2` `competition=La Liga`	wonTackle: 1.1317 -> 1.1553 totalShots: 0.3551 -> 0.3397 interceptionWon: 0.8827 -> 0.8687 wasFouled: 0.5128 -> 0.5027 fouls: 0.9778 -> 0.9718 totalCross: 0.1591 -> 0.1643
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Marc Casadó', 'matchup_zone': 'Right Wing vs Left Back — Flank 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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.0069 -> 0.0128 expected_assists: 0.0272 -> 0.0503
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 68.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0127` `goal_rate=0.0` `scorer_weight=0.0112`	-
`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=0.0491` `assist_rate=0.0` `provider_weight=0.0402`	-

Clemens Riedel D 86 0 0.01 0.00 620% 0 0.1 6.7 41.4 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 0.9974, quality 0.449)	`market_value_eur=3900000` `quality_factor=0.4486` `boost_factor=0.9974` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0112)	`blend_weight=0.0112` `history_matches=28` `season_overlap_discount=1.0` `per90_to_match_factor=0.9577` `prior_reliability=0.1133` `competition=La Liga`	fouls: 1.4847 -> 1.5058 interceptionWon: 0.8863 -> 0.8764 wonTackle: 0.6176 -> 0.6233
`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': 'Bil Nsongo', '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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_assists: 0.0085 -> 0.0157
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 70.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0083` `goal_rate=0.0` `scorer_weight=0.0076`	-
`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=0.0156` `assist_rate=0.0069` `provider_weight=0.0153`	-

Quilindschy Hartman D 87 0 0.03 0.01 372% 0 0.1 6.7 29.7 27 FBref Prior D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0017, quality 0.541)	`market_value_eur=11600000` `quality_factor=0.5411` `boost_factor=1.0017` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`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': 'Mario Soriano', 'matchup_zone': 'Left Wing vs Right Back — Flank 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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.0154 -> 0.0285 expected_assists: 0.0723 -> 0.1337
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0281` `goal_rate=0.0` `scorer_weight=0.0228`	-
`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=0.1251` `assist_rate=0.1128` `provider_weight=0.1671`	-

Javier Hernández M 79 0 0.20 0.07 202% 1 0.9 6.7 56.6 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 0.9976, quality 0.479)	`market_value_eur=6400000` `quality_factor=0.4793` `boost_factor=0.9976` `reference_quality=0.505` `history_matches=11` `history_shrink=0.3125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0339)	`blend_weight=0.0339` `history_matches=11` `season_overlap_discount=1.0` `per90_to_match_factor=0.8783` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.0082 -> 1.9521 fouls: 1.4545 -> 1.5004 wasFouled: 1.2202 -> 1.2622 goalAssist: 0.1971 -> 0.2261 interceptionWon: 0.6599 -> 0.6376
`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': 'Giacomo Quagliata', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.475, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9926, 'skill_edge': 0.003, 'height_edge': -0.008, 'attacker_skill': 0.4793, 'defender_skill': 0.4727, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Giacomo Quagliata', 'market_value': 4099999, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4727}], 'xg_override': 0.1071}	aerialWon: 0.1103 -> 0.9 totalShots: 1.1497 -> 1.1412 shotOffTarget: 0.7835 -> 0.7777
`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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.1071 -> 0.1981 expected_assists: 0.1261 -> 0.2333
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 86.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1797` `goal_rate=0.0727` `scorer_weight=0.1585`	-
`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=0.2081` `assist_rate=0.2261` `provider_weight=0.2916`	-

Edu Expósito M 84 0 0.14 0.08 67% 1 1.4 7.1 66.0 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 0.9986, quality 0.456)	`market_value_eur=4500000` `quality_factor=0.456` `boost_factor=0.9986` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0112)	`blend_weight=0.0112` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=0.9323` `prior_reliability=0.18` `competition=La Liga`	totalCross: 3.957 -> 3.9241 totalShots: 1.0719 -> 1.0951 interceptionWon: 1.088 -> 1.0796
`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': 'Ximo Navarro', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.484, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0064, 'skill_edge': 0.0084, 'height_edge': -0.004, 'attacker_skill': 0.456, 'defender_skill': 0.4374, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ximo Navarro', 'market_value': 95000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.074}	aerialWon: 0.6537 -> 0.9 totalShots: 1.0951 -> 1.1021
`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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.074 -> 0.1369 expected_assists: 0.1405 -> 0.26
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1279` `goal_rate=0.0947` `scorer_weight=0.1597`	-
`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=0.2289` `assist_rate=0.0951` `provider_weight=0.208`	-

Urko González M 76 0 0.09 0.02 468% 1 0.4 6.8 60.3 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0011, quality 0.541)	`market_value_eur=11600000` `quality_factor=0.5411` `boost_factor=1.0011` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0091)	`blend_weight=0.0091` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.8472` `prior_reliability=0.14` `competition=La Liga`	totalShots: 0.6489 -> 0.643
`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': 'Lorenzo Amatucci, Diego Villares', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.305, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0957, 'skill_edge': 0.0251, 'height_edge': 0.04, 'attacker_skill': 0.5481, 'defender_skill': 0.4922, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Lorenzo Amatucci', 'market_value': 10300000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.547}, {'player': 'Diego Villares', 'market_value': 1000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0483}	aerialWon: 0.5985 -> 1.3 totalShots: 0.6474 -> 0.7094 shotOffTarget: 0.4901 -> 0.537 onTargetScoringAttempt: 0.1573 -> 0.1724
`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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.0483 -> 0.0893 expected_assists: 0.0328 -> 0.0607
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 76.0)	`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=0.0854` `goal_rate=0.0524` `scorer_weight=0.093`	-
`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=0.0589` `assist_rate=0.0528` `provider_weight=0.0754`	-

Álex Calatrava M 76 0 0.20 0.09 112% 2 1.2 6.8 55.8 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9956, quality 0.461)	`market_value_eur=4900000` `quality_factor=0.4609` `boost_factor=0.9956` `reference_quality=0.505` `history_matches=10` `history_shrink=0.3333`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0361)	`blend_weight=0.0361` `history_matches=10` `season_overlap_discount=1.0` `per90_to_match_factor=0.8432` `prior_reliability=0.1667` `competition=La Liga`	fouls: 1.1742 -> 1.2049 onTargetScoringAttempt: 0.5284 -> 0.5577 wasFouled: 0.9373 -> 0.9156 totalShots: 1.4967 -> 1.5154 interceptionWon: 0.3462 -> 0.3581 goals: 0.1287 -> 0.1362 wonTackle: 1.5078 -> 1.5143
`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': 'Lorenzo Amatucci', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.398, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9677, 'skill_edge': -0.0339, 'height_edge': 0.012, 'attacker_skill': 0.4716, 'defender_skill': 0.547, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Lorenzo Amatucci', 'market_value': 10300000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.547}], 'xg_override': 0.1074}	aerialWon: 0.9722 -> 0.9 totalShots: 1.526 -> 1.4767 shotOffTarget: 0.9683 -> 0.937 onTargetScoringAttempt: 0.5577 -> 0.5397 bigChanceMissed: 0.1939 -> 0.1876
`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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.1074 -> 0.1987 expected_assists: 0.103 -> 0.1905
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 87.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1802` `goal_rate=0.1318` `scorer_weight=0.2295`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1735` `assist_rate=0.0958` `provider_weight=0.1815`	-

Pol Lozano M 79 0 0.09 0.03 247% 1 0.5 6.7 49.5 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9989, quality 0.472)	`market_value_eur=5800000` `quality_factor=0.472` `boost_factor=0.9989` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0019)	`blend_weight=0.0019` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.8754` `prior_reliability=0.0267` `competition=La Liga`	wonTackle: 1.1115 -> 1.1178
`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': 'Lorenzo Amatucci', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.408, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9822, 'skill_edge': -0.0281, 'height_edge': 0.016, 'attacker_skill': 0.4845, 'defender_skill': 0.547, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Lorenzo Amatucci', 'market_value': 10300000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.547}], 'xg_override': 0.0472}	aerialWon: 0.3301 -> 0.9 totalShots: 0.653 -> 0.6414 shotOffTarget: 0.4528 -> 0.4447
`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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.0472 -> 0.0873 expected_assists: 0.0479 -> 0.0886
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0836` `goal_rate=0.057` `scorer_weight=0.0961`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0848` `assist_rate=0.0542` `provider_weight=0.0943`	-

Roberto Fernández F 85 2 0.77 0.26 200% 2 1.4 6.7 62.8 34 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 1.0038, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0038` `reference_quality=0.505` `history_matches=49` `history_shrink=0.0926`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0116)	`blend_weight=0.0116` `history_matches=49` `season_overlap_discount=1.0` `per90_to_match_factor=0.9448` `prior_reliability=0.1933` `competition=La Liga`	fouls: 2.2257 -> 2.2112 totalOffside: 0.9712 -> 0.9599 goals: 0.3696 -> 0.3767 wasFouled: 1.1099 -> 1.1159
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'José María Giménez, Lucas Noubi', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.281, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1195, 'skill_edge': 0.0753, 'height_edge': 0.006, 'attacker_skill': 0.6408, 'defender_skill': 0.4735, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'José María Giménez', 'market_value': 5800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4955}, {'player': 'Lucas Noubi', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}], 'xg_override': 0.4184}	totalShots: 2.063 -> 2.3095 shotOffTarget: 1.233 -> 1.3803 onTargetScoringAttempt: 0.83 -> 0.9292 goals: 0.3767 -> 0.4217 expectedGoals: 0.3737 -> 0.4184 bigChanceMissed: 0.3407 -> 0.3814 expectedGoalsOnTarget: 0.2847 -> 0.3187
`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 1.85 (squad xG sum 1.0006, xG scale 1.8499, xA scale 1.8499, team xA 1.30 = 0.70 x lambda)	`scoreline_reset=true` `team_lambda=1.851` `squad_xg_sum=1.0006` `squad_xa_sum=0.7036` `team_expected_assists=1.3016` `team_xa_to_xg_ratio=0.7032`	expected_goals: 0.4184 -> 0.774 expected_assists: 0.0403 -> 0.0745
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 74.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=2` `goal_probability=0.5388` `goal_rate=0.4217` `scorer_weight=0.7794`	-
`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=0.0718` `assist_rate=0.0187` `provider_weight=0.0596`	-

Team totals 2 1.85 11 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Ángel Fortuño	G	4.4m	10.9%	Market-value substitute prior
Vanja Drkušić	D	19.9m	41.2%	Market-value substitute prior
Unai Núñez	D	13.6m	21.7%	Market-value substitute prior
Gabriel Moscardo	M	34.7m	69.6%	Market-value substitute prior
Rafael Bauzà	M	22.0m	69.2%	Market-value substitute prior
Tyrhys Dolan	F	25.7m	34.2%	Market-value substitute prior

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

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

Leo Román G 85 0 0.00 - n/a 0.0 7.1 62.3 35 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0001, quality 0.507)	`market_value_eur=8700000` `quality_factor=0.5071` `boost_factor=1.0001` `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': 'Roberto Fernández, Álex Calatrava', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.4025}`	-
`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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	shots_faced: 13.3 -> 17.6 expected_saves: 3.25 -> 4.31 high_pressure_saves: 1.12 -> 1.48
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=1.1493`	-
`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=0.8384`	-

Ximo Navarro D 78 0 0.05 0.02 165% 0 0.3 6.7 39.5 13 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.437)	`market_value_eur=95000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Edu Expósito', '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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.0333 -> 0.0517 expected_assists: 0.0126 -> 0.0196
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 72.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0504` `goal_rate=0.0` `scorer_weight=0.0414`	-
`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=0.0194` `assist_rate=0.0` `provider_weight=0.0157`	-

Giacomo Quagliata D 81 0 0.04 0.02 131% 1 0.4 6.7 46.4 14 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 0.9946, quality 0.451)	`market_value_eur=4099999` `quality_factor=0.4511` `boost_factor=0.9946` `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': 'Javier Hernández', '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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.027 -> 0.0419 expected_assists: 0.0863 -> 0.134
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 73.0)	`match_squad_rank=17` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.041` `goal_rate=0.0` `scorer_weight=0.0335`	-
`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=0.1254` `assist_rate=0.0` `provider_weight=0.1072`	-

José María Giménez D 80 0 0.09 0.04 143% 1 0.4 6.9 45.7 27 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 0.9983, quality 0.472)	`market_value_eur=5800000` `quality_factor=0.472` `boost_factor=0.9983` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.0607 -> 0.0942 expected_assists: 0.0182 -> 0.0283
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 82.0)	`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=0.0899` `goal_rate=0.0` `scorer_weight=0.0754`	-
`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=0.0279` `assist_rate=0.0416` `provider_weight=0.0354`	-

Lucas Noubi D 90 0 0.00 - n/a 1 0.0 6.8 25.8 13 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 0.9901, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.9901` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_assists: 0.0102 -> 0.0158
`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=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0157` `assist_rate=0.0` `provider_weight=0.0131`	-

Mario Soriano M 80 0 0.09 0.05 102% 1 0.9 7.2 50.6 14 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 0.9965, quality 0.470)	`market_value_eur=5600000` `quality_factor=0.4695` `boost_factor=0.9965` `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': 'Quilindschy Hartman', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.363, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8281, 'skill_edge': -0.0569, 'height_edge': -0.06, 'attacker_skill': 0.4695, 'defender_skill': 0.5961, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Quilindschy Hartman', 'market_value': 11600000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.5961}], 'xg_override': 0.0596}	aerialWon: 0.2269 -> 0.6 totalShots: 1.2861 -> 1.065 shotOffTarget: 1.0298 -> 0.8528 onTargetScoringAttempt: 0.2563 -> 0.2122 expectedGoalsOnTarget: 0.0992 -> 0.0821 goals: 0.0844 -> 0.0699 expectedGoals: 0.072 -> 0.0596
`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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.0596 -> 0.0925 expected_assists: 0.1347 -> 0.209
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 75.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0884` `goal_rate=0.0699` `scorer_weight=0.1012`	-
`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=0.1886` `assist_rate=0.1063` `provider_weight=0.1769`	-

Lorenzo Amatucci M 88 0 0.07 0.02 174% 1 0.1 6.9 46.2 12 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 1.0024, quality 0.526)	`market_value_eur=10300000` `quality_factor=0.526` `boost_factor=1.0024` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Álex Calatrava', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.442, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0323, 'skill_edge': 0.0339, 'height_edge': -0.012, 'attacker_skill': 0.547, 'defender_skill': 0.4716, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Álex Calatrava', 'market_value': 4900000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4716}], 'xg_override': 0.0435}	aerialWon: 1.2176 -> 0.8 totalShots: 0.5222 -> 0.5391 shotOffTarget: 0.3783 -> 0.3905 bigChanceMissed: 0.2213 -> 0.2284
`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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.0435 -> 0.0675 expected_assists: 0.0344 -> 0.0534
`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=0.0653` `goal_rate=0.0509` `scorer_weight=0.0728`	-
`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=0.052` `assist_rate=0.0463` `provider_weight=0.0609`	-

Riki Rodríguez M 65 0 0.09 0.02 511% 1 0.2 6.7 35.1 13 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 0.9916, quality 0.437)	`market_value_eur=1400000` `quality_factor=0.4374` `boost_factor=0.9916` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Álex Calatrava, Pol Lozano', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.22, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9702, 'skill_edge': -0.0183, 'height_edge': -0.002, 'attacker_skill': 0.4374, 'defender_skill': 0.478, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Álex Calatrava', 'market_value': 4900000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4716}, {'player': 'Pol Lozano', 'market_value': 5800000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4845}], 'xg_override': 0.0591}	aerialWon: 0.1932 -> 0.9 totalShots: 0.7408 -> 0.7187 shotOffTarget: 0.5525 -> 0.536 onTargetScoringAttempt: 0.1882 -> 0.1826
`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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.0591 -> 0.0918 expected_assists: 0.0311 -> 0.0483
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 77.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_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=0.0877` `goal_rate=0.0604` `scorer_weight=0.0929`	-
`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=0.0472` `assist_rate=0.0504` `provider_weight=0.0598`	-

Diego Villares M 67 0 0.11 0.04 196% 1 0.3 6.9 31.7 13 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 0.9908, quality 0.437)	`market_value_eur=1000000` `quality_factor=0.4374` `boost_factor=0.9908` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Álex Calatrava', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.449, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0421, 'skill_edge': -0.0154, 'height_edge': 0.044, 'attacker_skill': 0.4374, 'defender_skill': 0.4716, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Álex Calatrava', 'market_value': 4900000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4716}], 'xg_override': 0.0684}	aerialWon: 0.2783 -> 1.2 totalShots: 0.7815 -> 0.8144 bigChanceMissed: 0.5753 -> 0.5995 shotOffTarget: 0.5603 -> 0.5839 onTargetScoringAttempt: 0.2212 -> 0.2305
`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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.0684 -> 0.1062 expected_assists: 0.0441 -> 0.0685
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 79.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1008` `goal_rate=0.068` `scorer_weight=0.1058`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0662` `assist_rate=0.0557` `provider_weight=0.0769`	-

Marc Casadó M 70 0 0.09 0.02 259% 0 0.1 6.9 32.6 27 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 1.0032, quality 0.574)	`market_value_eur=14500000` `quality_factor=0.5737` `boost_factor=1.0032` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Roger Hinojo', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.501, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0314, 'skill_edge': 0.0534, 'height_edge': -0.032, 'attacker_skill': 0.5737, 'defender_skill': 0.4551, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Roger Hinojo', 'market_value': 3100000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.4551}], 'xg_override': 0.0566}	aerialWon: 0.4609 -> 0.8 totalShots: 0.4683 -> 0.483 shotOffTarget: 0.3354 -> 0.3459
`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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.0566 -> 0.0879 expected_assists: 0.0405 -> 0.0629
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 78.0)	`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=0.0841` `goal_rate=0.0724` `scorer_weight=0.1009`	-
`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=0.0548` `provider_weight=0.0728`	-

Bil Nsongo F 71 1 0.33 0.11 203% 2 1.5 6.7 48.9 15 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9961, quality 0.466)	`market_value_eur=5300000` `quality_factor=0.4659` `boost_factor=0.9961` `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': 'Leandro Cabrera, Clemens Riedel', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.183, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9745, 'skill_edge': 0.0067, 'height_edge': -0.024, 'attacker_skill': 0.4659, 'defender_skill': 0.451, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Clemens Riedel', 'market_value': 3900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4646}], 'xg_override': 0.2134}	totalShots: 1.8388 -> 1.7919 shotOffTarget: 1.2445 -> 1.2128 onTargetScoringAttempt: 0.5942 -> 0.579 goals: 0.2227 -> 0.217 expectedGoals: 0.219 -> 0.2134
`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 1.13 (squad xG sum 0.7291, xG scale 1.5526, xA scale 1.5526, team xA 0.86 = 0.76 x lambda)	`scoreline_reset=true` `team_lambda=1.132` `squad_xg_sum=0.7291` `squad_xa_sum=0.5542` `team_expected_assists=0.8605` `team_xa_to_xg_ratio=0.7602`	expected_goals: 0.2134 -> 0.3315 expected_assists: 0.0449 -> 0.0697
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 69.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2822` `goal_rate=0.217` `scorer_weight=0.336`	-
`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=0.0673` `assist_rate=0.0` `provider_weight=0.0558`	-

Team totals 1 1.13 11 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Álvaro Ferllo	G	4.4m	10.9%	Market-value substitute prior
Bright Ede	D	13.7m	30.6%	Market-value substitute prior
Adrià Altimira	D	13.6m	29.9%	Market-value substitute prior
Angeliño	M	22.0m	50.0%	Market-value substitute prior
Noé Carrillo	M	22.0m	49.9%	Market-value substitute prior
Yeremay Hernández	F	26.2m	59.9%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Urko González vs Marc Casadó will be the pivotal duel. Total antagonist xG — Home: 0.80, Away: 0.50. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.0% / 50.0%, dominance ratio 0.50, key duel: Urko González vs Marc Casadó

Javier Hernández xG 0.11Edu Expósito xG 0.07Urko González xG 0.05Mario Soriano xG 0.06Marc Casadó xG 0.06Riki Rodríguez xG 0.06

Summary

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

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Urko González vs Marc Casadó will be the pivotal duel. Total antagonist xG — Home: 0.80, Away: 0.50. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Arsenal vs Hull

Premier League · 20261107 · 4-2-3-1 vs 5-4-1

Predicted 1-0Winner: ArsenalWinning H 1-0 (12.0%)Winning A 0-1 (5.0%)Confidence 0.72λ home/away 1.98 / 0.82Most-likely P 12.0%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Arsenal vs Hull. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 5-4-1 (duel lambdas: Home 2.172, Away 1.062). Final calibrated Poisson lambdas: Home 1.976, Away 0.820 (most likely score 1-0).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 2.17 / 1.06 Final λ (H/A) 1.98 / 0.82

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

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Arsenal	Hull
League position	2.00	10.00
Points per game	2.08	1.28
Attack index	1.07	0.91
Defense (concede) index	0.88	0.78
Form multiplier	1.04	0.96
Standing λ multiplier	0.98	0.87

Lambda decomposition (how the goal rates were built)

Stage	Arsenal λ	Hull λ
FBref Squad Prior E[λ] (weight 0.192)	2.069	2.069
Pre-mismatch	2.281	1.009
Pre-calibration (Micro-duels)	2.172	1.062
Final λ	1.976	0.820

competition calibration scale 0.85competition observed total goals 2.781quality gap applied Truemismatch score pressure applied Truecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
1-0	12.0%
2-0	11.9%
1-1	10.0%
2-1	9.8%
3-0	7.8%

Home win	64.4%
Draw	20.9%
Away win	14.7%
Over 2.5	53.0%
BTTS yes	48.3%

Pregame fair line — favorite Arsenal (64.4%), fair total 2.80, fair spread 1.16

Projected players vs season baseline

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

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

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

David Raya G 90 0 0.00 - n/a 0.0 7.1 56.6 32 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0070, quality 0.739)	`market_value_eur=33000000` `quality_factor=0.7389` `boost_factor=1.007` `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`	saves: 2.9289 -> 2.9079 wasFouled: 0.7105 -> 0.7043
`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': 'Oliver McBurnie, Tim Iroegbunam', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.0616}`	-
`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 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	shots_faced: 10.1 -> 7.8 expected_saves: 2.47 -> 1.91 high_pressure_saves: 0.85 -> 0.66
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 88.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=2.0855`	-
`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=1.5615`	-

William Saliba D 90 0 0.03 0.03 ok 0 0.1 7.0 53.3 21 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0161, quality 0.891)	`market_value_eur=94000000` `quality_factor=0.891` `boost_factor=1.0161` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`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': 'Oliver McBurnie', '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 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0258 -> 0.0343 expected_assists: 0.0747 -> 0.0924
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 88.0)	`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=0.0337` `goal_rate=0.0493` `scorer_weight=0.0429`	-
`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=0.0883` `assist_rate=0.0` `provider_weight=0.0739`	-

Ben White D 75 0 0.03 0.01 183% 0 0.1 6.9 36.2 27 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0142, quality 0.732)	`market_value_eur=32000000` `quality_factor=0.732` `boost_factor=1.0142` `reference_quality=0.505` `history_matches=19` `history_shrink=0.2083`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0181)	`blend_weight=0.0181` `history_matches=19` `season_overlap_discount=1.0` `per90_to_match_factor=0.8366` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 1.7465 -> 1.7603 wasFouled: 0.9206 -> 0.9115
`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': 'Elliot Stroud', 'matchup_zone': 'Right Mid vs Left Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0206 -> 0.0274 expected_assists: 0.1179 -> 0.1458
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 86.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.027` `goal_rate=0.0` `scorer_weight=0.0219`	-
`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=0.1357` `assist_rate=0.363` `provider_weight=0.1823`	-

Gabriel Magalhães D 90 0 0.27 0.10 186% 1 0.8 7.1 59.4 33 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0122, quality 0.871)	`market_value_eur=70000000` `quality_factor=0.8707` `boost_factor=1.0122` `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=0.9997` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.8153 -> 0.8075 fouls: 0.82 -> 0.8265 onTargetScoringAttempt: 0.5264 -> 0.5213
`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': 'Oliver McBurnie', '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 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2057 -> 0.2733 expected_assists: 0.0365 -> 0.0452
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 88.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2391` `goal_rate=0.1574` `scorer_weight=0.2217`	-
`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=0.0442` `assist_rate=0.0221` `provider_weight=0.0377`	-

Myles Lewis-Skelly D 74 0 0.03 0.01 153% 1 0.2 6.8 32.6 36 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 1.0176, quality 0.869)	`market_value_eur=69000000` `quality_factor=0.8692` `boost_factor=1.0176` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0126)	`blend_weight=0.0126` `history_matches=26` `season_overlap_discount=1.0` `per90_to_match_factor=0.8218` `prior_reliability=0.12` `competition=Premier League`	fouls: 1.4186 -> 1.4065 wonTackle: 0.7693 -> 0.7596
`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': 'Regan Slater', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0213 -> 0.0283 expected_assists: 0.0944 -> 0.1168
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 78.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0279` `goal_rate=0.0` `scorer_weight=0.0226`	-
`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=0.1102` `assist_rate=0.0` `provider_weight=0.0934`	-

Declan Rice M 86 0 0.11 0.04 166% 1 0.6 7.3 59.1 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 1.0120, quality 0.897)	`market_value_eur=114000000` `quality_factor=0.8967` `boost_factor=1.012` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0075)	`blend_weight=0.0075` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9503` `prior_reliability=0.1133` `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': 'John Egan', 'matchup_zone': 'LW vs CB', 'duel_win_rate': 0.639, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.3214, 'skill_edge': 0.2067, 'height_edge': 0.012, 'attacker_skill': 0.8967, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'John Egan', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.0834}`	totalShots: 0.9942 -> 1.3137 shotOffTarget: 0.7469 -> 0.987 aerialWon: 0.988 -> 1.2 onTargetScoringAttempt: 0.2444 -> 0.323 goals: 0.0853 -> 0.1127 expectedGoals: 0.0631 -> 0.0834
`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 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0834 -> 0.1108 expected_assists: 0.2143 -> 0.265
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 88.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1049` `goal_rate=0.1127` `scorer_weight=0.1351`	-
`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=0.2328` `assist_rate=0.2552` `provider_weight=0.306`	-

Martin Ødegaard M 83 0 0.35 0.10 253% 2 0.7 7.3 51.9 26 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0155, quality 0.888)	`market_value_eur=88000000` `quality_factor=0.8879` `boost_factor=1.0155` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0094)	`blend_weight=0.0094` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.9177` `prior_reliability=0.1067` `competition=Premier League`	wonTackle: 0.3892 -> 0.4017
`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': 'John Egan', 'matchup_zone': 'RW vs CB', 'duel_win_rate': 0.595, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2568, 'skill_edge': 0.2027, 'height_edge': -0.028, 'attacker_skill': 0.8879, 'defender_skill': 0.4374, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'John Egan', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.2619}`	aerialWon: 0.0502 -> 1.0 totalShots: 1.9598 -> 2.4631 shotOffTarget: 1.1923 -> 1.4985 onTargetScoringAttempt: 0.7627 -> 0.9586 goals: 0.2787 -> 0.3503 expectedGoals: 0.2084 -> 0.2619 bigChanceMissed: 0.1196 -> 0.1503 expectedGoalsOnTarget: 0.0911 -> 0.1145
`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 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2619 -> 0.3479 expected_assists: 0.2063 -> 0.2552
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 86.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2938` `goal_rate=0.3503` `scorer_weight=0.4349`	-
`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=0.2252` `assist_rate=0.2328` `provider_weight=0.2816`	-

Eberechi Eze M 71 0 0.18 0.08 127% 2 1.1 6.8 49.4 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 1.0121, quality 0.859)	`market_value_eur=63000000` `quality_factor=0.8589` `boost_factor=1.0121` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0034)	`blend_weight=0.0034` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.794` `prior_reliability=0.0467` `competition=Premier League`	wasFouled: 1.5846 -> 1.5909
`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 Crooks', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.552, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1946, 'skill_edge': 0.1924, 'height_edge': -0.06, 'attacker_skill': 0.865, 'defender_skill': 0.4374, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Matt Crooks', 'market_value': 1000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}], 'xg_override': 0.1364}`	aerialWon: 0.3971 -> 1.0 totalShots: 1.5033 -> 1.7958 shotOffTarget: 1.0325 -> 1.2334 onTargetScoringAttempt: 0.4703 -> 0.5618 expectedGoalsOnTarget: 0.2375 -> 0.2837 goals: 0.1165 -> 0.1392 expectedGoals: 0.1142 -> 0.1364
`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 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1364 -> 0.1812 expected_assists: 0.077 -> 0.0952
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 84.0)	`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=0.1657` `goal_rate=0.1392` `scorer_weight=0.1839`	-
`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=0.0908` `assist_rate=0.0703` `provider_weight=0.0902`	-

Bruno Guimarães M 79 0 0.11 0.12 ok 1 0.8 7.1 52.8 24 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0140, quality 0.879)	`market_value_eur=77000000` `quality_factor=0.8792` `boost_factor=1.014` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0011)	`blend_weight=0.0011` `history_matches=35` `season_overlap_discount=1.0` `per90_to_match_factor=0.8807` `prior_reliability=0.0133` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Matt Crooks, Tim Iroegbunam', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0808 -> 0.1073 expected_assists: 0.1143 -> 0.1414
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 86.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1017` `goal_rate=0.0935` `scorer_weight=0.1177`	-
`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=0.1319` `assist_rate=0.0989` `provider_weight=0.1282`	-

Mikel Merino M 77 0 0.20 0.10 89% 2 0.8 6.8 41.2 18 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 1.0078, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0078` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0025)	`blend_weight=0.0025` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.8559` `prior_reliability=0.0267` `competition=Premier League`	fouls: 1.3666 -> 1.3791 wasFouled: 1.5574 -> 1.5641 totalShots: 1.7345 -> 1.7411
`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': 'Regan Slater', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1488 -> 0.1977 expected_assists: 0.0665 -> 0.0823
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 83.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1794` `goal_rate=0.1301` `scorer_weight=0.1791`	-
`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=0.079` `assist_rate=0.0526` `provider_weight=0.0725`	-

Bukayo Saka F 85 1 0.51 0.29 78% 3 1.9 7.2 59.3 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0137, quality 0.897)	`market_value_eur=115000000` `quality_factor=0.8968` `boost_factor=1.0137` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0086)	`blend_weight=0.0086` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9417` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 2.5768 -> 2.5879 totalCross: 3.9217 -> 3.9308 fouls: 1.0385 -> 1.0296 goals: 0.3271 -> 0.3338
`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': 'John Egan, Semi Ajayi', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.363, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.2392, 'skill_edge': 0.2067, 'height_edge': -0.044, 'attacker_skill': 0.8968, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'John Egan', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Semi Ajayi', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.3839}	totalShots: 2.369 -> 2.9357 shotOffTarget: 1.3394 -> 1.6598 onTargetScoringAttempt: 1.0272 -> 1.2729 bigChanceMissed: 0.4955 -> 0.614 expectedGoalsOnTarget: 0.4303 -> 0.5332 goals: 0.3338 -> 0.4136 expectedGoals: 0.3098 -> 0.3839
`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 1.98 (squad xG sum 1.4874, xG scale 1.3285, xA scale 1.2370, team xA 1.58 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.976` `squad_xg_sum=1.4874` `squad_xa_sum=1.2779` `team_expected_assists=1.5808` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.3839 -> 0.5099 expected_assists: 0.1994 -> 0.2467
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 87.0)	`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=1` `goal_probability=0.3994` `goal_rate=0.4136` `scorer_weight=0.5448`	-
`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=0.2186` `assist_rate=0.0961` `provider_weight=0.1974`	-

Team totals 1 1.98 15 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Illan Meslier	G	4.5m	11.5%	Market-value substitute prior
Jurriën Timber	D	15.3m	37.7%	Market-value substitute prior
Riccardo Calafiori	D	15.2m	25.1%	Market-value substitute prior
Martín Zubimendi	M	18.9m	72.7%	Market-value substitute prior
Max Dowman	M	23.5m	57.0%	Market-value substitute prior
Kai Havertz	F	26.9m	36.7%	Market-value substitute prior

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

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

Konstantinos Tzolakis G 90 0 0.00 - n/a 0.0 6.9 44.8 14 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 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': 'Bukayo Saka, Martin Ødegaard', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 2.1716}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	shots_faced: 20.6 -> 18.8 expected_saves: 5.04 -> 4.6 high_pressure_saves: 1.74 -> 1.58
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 79.0)	`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=0.0` `scorer_weight=0.0` `squad_weight_total=0.8559`	-
`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=0.6106`	-

Lewie Coyle D 79 0 0.03 0.02 94% 0 0.2 6.6 41.6 14 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9928, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9928` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0201)	`blend_weight=0.0201` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8802` `prior_reliability=0.0867` `competition=Premier League`	wasFouled: 0.7366 -> 0.7763 fouls: 0.234 -> 0.2565 totalCross: 2.3774 -> 2.3568 totalShots: 0.4645 -> 0.4552
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Martin Ødegaard, Myles Lewis-Skelly', 'matchup_zone': 'LWB vs RW + RB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 70.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0339` `goal_rate=0.0` `scorer_weight=0.0276`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0132` `assist_rate=0.0` `provider_weight=0.0111`	-

John Egan D 82 0 0.05 0.02 145% 0 0.4 6.7 44.1 14 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9928, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9928` `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=0.909` `prior_reliability=0.1333` `competition=Premier League`	totalShots: 0.4993 -> 0.4838 wonTackle: 0.8202 -> 0.8089 fouls: 0.2451 -> 0.2375
`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': 'Declan Rice', 'matchup_zone': 'LW vs CB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0207 -> 0.0276
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 72.0)	`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=0.0446` `goal_rate=0.0` `scorer_weight=0.0365`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0272` `assist_rate=0.0` `provider_weight=0.0221`	-

Semi Ajayi D 89 0 0.04 0.05 ok 0 0.2 6.8 43.9 14 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9928, quality 0.437)	`market_value_eur=930000` `quality_factor=0.4374` `boost_factor=0.9928` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0263)	`blend_weight=0.0263` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9874` `prior_reliability=0.1133` `competition=Premier League`	wonTackle: 1.2722 -> 1.254 goals: 0.0528 -> 0.0667 onTargetScoringAttempt: 0.0528 -> 0.0667 wasFouled: 0.0621 -> 0.0757 fouls: 0.4317 -> 0.4203
`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': 'Bukayo Saka', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 70.0)	`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=0.043` `goal_rate=0.0667` `scorer_weight=0.055`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0079` `assist_rate=0.0` `provider_weight=0.0071`	-

Nobel Mendy D 77 0 0.08 0.04 104% 1 0.3 6.8 48.9 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0058, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0058` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0081)	`blend_weight=0.0081` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.8589` `prior_reliability=0.0867` `competition=Premier League`	onTargetScoringAttempt: 0.2585 -> 0.2667 interceptionWon: 0.9919 -> 0.9839 fouls: 1.5087 -> 1.5019 totalShots: 0.4929 -> 0.4992
`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': 'Bukayo Saka', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.071 -> 0.0793
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 75.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0762` `goal_rate=0.0999` `scorer_weight=0.0982`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0096` `assist_rate=0.0` `provider_weight=0.0084`	-

Ryan Giles D 83 0 0.00 0.00 ok 0 0.1 6.6 42.4 14 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0074, quality 0.574)	`market_value_eur=14500000` `quality_factor=0.5737` `boost_factor=1.0074` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0294)	`blend_weight=0.0294` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9237` `prior_reliability=0.1267` `competition=Premier League`	totalCross: 6.7403 -> 6.7279 fouls: 0.3353 -> 0.3254 interceptionWon: 0.7394 -> 0.732
`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': 'Declan Rice, Ben White', 'matchup_zone': 'RWB vs LW + LB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0547 -> 0.073
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 18 by projected rating, fifa_overall 72.0)	`match_squad_rank=18` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0016` `goal_rate=0.0` `scorer_weight=0.0016`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0704` `assist_rate=0.1052` `provider_weight=0.0912`	-

Regan Slater M 85 0 0.06 0.02 154% 1 0.6 6.8 43.6 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 1.0009, quality 0.513)	`market_value_eur=9200000` `quality_factor=0.513` `boost_factor=1.0009` `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=0.9434` `prior_reliability=0.1333` `competition=Premier League`	totalShots: 1.0386 -> 1.0065 fouls: 0.6782 -> 0.701 interceptionWon: 0.4561 -> 0.442 goalAssist: 0.0794 -> 0.0915 onTargetScoringAttempt: 0.3058 -> 0.2963 totalCross: 1.1502 -> 1.1438
`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': 'Myles Lewis-Skelly', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel', 'duel_win_rate': 0.275, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7273, 'skill_edge': -0.1655, 'height_edge': -0.02, 'attacker_skill': 0.5251, 'defender_skill': 0.8928, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Myles Lewis-Skelly', 'market_value': 69000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8928}], 'xg_override': 0.0521}	totalShots: 1.0291 -> 0.7485 shotOffTarget: 0.7328 -> 0.533 onTargetScoringAttempt: 0.2963 -> 0.2155 aerialWon: 0.9208 -> 0.9 expectedGoals: 0.0717 -> 0.0521 goals: 0.0699 -> 0.0508
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0521 -> 0.0582 expected_assists: 0.07 -> 0.0934
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 72.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0565` `goal_rate=0.0508` `scorer_weight=0.0575`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0892` `assist_rate=0.0915` `provider_weight=0.1101`	-

Elliot Stroud M 72 0 0.05 0.00 901% 1 0.2 6.7 32.9 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 0.9998, quality 0.503)	`market_value_eur=8400000` `quality_factor=0.5035` `boost_factor=0.9998` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0253)	`blend_weight=0.0253` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.8026` `prior_reliability=0.0933` `competition=Premier League`	totalCross: 0.4872 -> 0.5183 interceptionWon: 0.4733 -> 0.4903 wonTackle: 0.5923 -> 0.6063 wasFouled: 0.2047 -> 0.1995 onTargetScoringAttempt: 0.2013 -> 0.1962
`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': 'Ben White', 'matchup_zone': 'Right Mid vs Left Back — Wide Channel', 'duel_win_rate': 0.324, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8002, 'skill_edge': -0.1319, 'height_edge': -0.004, 'attacker_skill': 0.5146, 'defender_skill': 0.8077, 'attacker_role': 'RM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Ben White', 'market_value': 32000000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.8077}], 'xg_override': 0.042}	aerialWon: 0.5216 -> 1.2 totalShots: 0.7192 -> 0.5755 shotOffTarget: 0.522 -> 0.4177 onTargetScoringAttempt: 0.1962 -> 0.157 goals: 0.0592 -> 0.0474 expectedGoals: 0.0525 -> 0.042
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0433 -> 0.0578
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 74.0)	`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=0.0458` `goal_rate=0.0474` `scorer_weight=0.0497`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0562` `assist_rate=0.0646` `provider_weight=0.071`	-

Matt Crooks M 72 0 0.04 - n/a 0 0.0 6.7 32.8 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9908, quality 0.437)	`market_value_eur=1000000` `quality_factor=0.4374` `boost_factor=0.9908` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0197)	`blend_weight=0.0197` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.7976` `prior_reliability=0.0667` `competition=Premier League`	wonTackle: 1.2986 -> 1.3202 totalShots: 0.5707 -> 0.5595 fouls: 2.0268 -> 2.0183 wasFouled: 0.4066 -> 0.4143
`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': 'Bruno Guimarães', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.291, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7657, 'skill_edge': -0.2034, 'height_edge': 0.044, 'attacker_skill': 0.4374, 'defender_skill': 0.8893, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Bruno Guimarães', 'market_value': 77000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8893}], 'xg_override': 0.0315}	aerialWon: 1.0767 -> 1.4 totalShots: 0.5673 -> 0.4344 shotOffTarget: 0.3986 -> 0.3052 onTargetScoringAttempt: 0.1687 -> 0.1292 goals: 0.0611 -> 0.0468 expectedGoals: 0.0411 -> 0.0315
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0265 -> 0.0354
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 71.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0346` `goal_rate=0.0468` `scorer_weight=0.0418`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0348` `assist_rate=0.052` `provider_weight=0.0442`	-

Tim Iroegbunam M 81 0 0.08 0.03 189% 1 0.4 6.8 44.4 29 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0029, quality 0.585)	`market_value_eur=15500000` `quality_factor=0.5846` `boost_factor=1.0029` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Bruno Guimarães', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.321, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8105, 'skill_edge': -0.1289, 'height_edge': 0.0, 'attacker_skill': 0.6029, 'defender_skill': 0.8893, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Bruno Guimarães', 'market_value': 77000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8893}], 'xg_override': 0.0747}	totalShots: 1.1492 -> 0.9314 shotOffTarget: 0.8265 -> 0.6699 onTargetScoringAttempt: 0.3227 -> 0.2615 aerialWon: 1.1209 -> 1.1 expectedGoals: 0.0922 -> 0.0747 goals: 0.0673 -> 0.0545 expectedGoalsOnTarget: 0.0576 -> 0.0467
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0747 -> 0.0835 expected_assists: 0.0387 -> 0.0517
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 76.0)	`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=0.0801` `goal_rate=0.0545` `scorer_weight=0.07`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0504` `assist_rate=0.0539` `provider_weight=0.0606`	-

Oliver McBurnie F 87 0 0.25 0.16 57% 2 0.9 6.8 44.3 14 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9988, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9988` `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=0.9674` `prior_reliability=0.1333` `competition=Premier League`	totalShots: 1.9287 -> 1.899 wasFouled: 1.6175 -> 1.6423 goals: 0.3555 -> 0.3445 goalAssist: 0.2815 -> 0.2728 interceptionWon: 0.2675 -> 0.2592 onTargetScoringAttempt: 0.7013 -> 0.7095 fouls: 1.2368 -> 1.2434 totalOffside: 0.195 -> 0.189
`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': 'William Saliba, Gabriel Magalhães', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7145, 'skill_edge': -0.1802, 'height_edge': -0.014, 'attacker_skill': 0.4939, 'defender_skill': 0.8944, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'William Saliba', 'market_value': 94000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8981}, {'player': 'Gabriel Magalhães', 'market_value': 70000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8907}], 'xg_override': 0.2232}	totalShots: 1.9369 -> 1.3839 shotOffTarget: 1.2274 -> 0.877 onTargetScoringAttempt: 0.7095 -> 0.5069 goals: 0.3445 -> 0.2461 expectedGoals: 0.3124 -> 0.2232 expectedGoalsOnTarget: 0.238 -> 0.1701 bigChanceMissed: 0.2131 -> 0.1523
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 0.7338, xG scale 1.1175, xA scale 1.3349, team xA 0.53 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.82` `squad_xg_sum=0.7338` `squad_xa_sum=0.3993` `team_expected_assists=0.533` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2232 -> 0.2495 expected_assists: 0.0313 -> 0.0418
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 75.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.2208` `goal_rate=0.2461` `scorer_weight=0.2704`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0409` `assist_rate=0.2728` `provider_weight=0.0522`	-

Team totals 0 0.82 8 6.7

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Jack Butland	G	4.4m	10.9%	Market-value substitute prior
Lucas Herrington	D	22.9m	61.5%	Market-value substitute prior
Charlie Hughes	D	13.9m	31.2%	Market-value substitute prior
Christos Mouzakitis	M	22.8m	53.5%	Market-value substitute prior
Brooke Norton-Cuffy	M	22.6m	52.5%	Market-value substitute prior
Robinio Vaz	F	26.0m	59.1%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~53% possession expected (Declan Rice vs Tim Iroegbunam). Total antagonist xG — Home: 0.87, Away: 0.45. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 53.3% / 46.7%, dominance ratio 0.62, key duel: Declan Rice vs Tim Iroegbunam

Declan Rice xG 0.08Eberechi Eze xG 0.14Martin Ødegaard xG 0.26Oliver McBurnie xG 0.22Regan Slater xG 0.05Elliot Stroud xG 0.04

Summary

Antagonist matchup analysis for Arsenal vs Hull. Most likely scoreline: 1-0. Lambdas derived from 4 home and 7 away individual player duels. Head-to-head: Arsenal 8W-2D-0L vs Hull over 10 meetings.

Tactical parity between 4-2-3-1 and 5-4-1. Match outcome driven primarily by individual player quality. Home midfield dominates with ~53% possession expected (Declan Rice vs Tim Iroegbunam). Total antagonist xG — Home: 0.87, Away: 0.45. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Forest vs Man City

Premier League · 20261107 · 3-4-2-1 vs 4-2-3-1

Predicted 0-1Winner: Man CityWinning H 1-0 (6.1%)Winning A 0-1 (10.3%)Confidence 0.69λ home/away 1.07 / 1.78Most-likely P 10.3%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Forest vs Man City. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 3-4-2-1 vs 4-2-3-1 (duel lambdas: Home 1.242, Away 2.083). Final calibrated Poisson lambdas: Home 1.067, Away 1.780 (most likely score 0-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.24 / 2.08 Final λ (H/A) 1.07 / 1.78

FBref Team Priors: Nottingham Forest (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 2.069) vs Manchester City (Gls/90: 3.0, GA/90: 3.0 → E[λ]: 2.069) | Blend Weight: 0.192

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Forest	Man City
League position	19.00	1.00
Points per game	0.94	1.94
Attack index	0.82	1.21
Defense (concede) index	0.88	1.04
Form multiplier	0.95	1.05
Standing λ multiplier	0.87	1.11

Lambda decomposition (how the goal rates were built)

Stage	Forest λ	Man City λ
FBref Squad Prior E[λ] (weight 0.192)	2.069	2.069
Pre-mismatch	1.206	2.143
Pre-competitive-floor	1.171	2.364
Pre-calibration (Micro-duels)	1.242	2.083
Final λ	1.067	1.780

Scoreline distribution & markets

Top 5 scorelines	P
1-1	11.1%
0-1	10.3%
1-2	9.8%
0-2	9.2%
1-0	6.1%

Home win	22.6%
Draw	23.4%
Away win	54.0%
Over 2.5	54.2%
BTTS yes	54.6%

Pregame fair line — favorite Man City (54.0%), fair total 2.85, fair spread -0.71

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.

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

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

Matz Sels G 90 0 0.00 - n/a 0.0 7.0 57.0 30 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9980, quality 0.446)	`market_value_eur=3700000` `quality_factor=0.4461` `boost_factor=0.998` `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=0.9972` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.8442 -> 2.836
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Erling Haaland, Rayan Cherki', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 2.0832}`	-
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	shots_faced: 19.8 -> 16.9 expected_saves: 4.85 -> 4.13 high_pressure_saves: 1.67 -> 1.42
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 81.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.0916`	-
`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=0.6575`	-

Murillo D 88 0 0.08 0.06 33% 1 0.8 6.9 56.0 26 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 1.0121, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0121` `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=0.9806` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.333 -> 1.3236 totalShots: 1.3045 -> 1.2955 wonTackle: 1.1854 -> 1.1777 fouls: 1.14 -> 1.1328
`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': 'Enzo Fernández', 'matchup_zone': 'LW vs CB'}`	-
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1121 -> 0.0778 expected_assists: 0.0474 -> 0.0341
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 82.0)	`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=0.0749` `goal_rate=0.0028` `scorer_weight=0.0622`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0335` `assist_rate=0.0668` `provider_weight=0.0409`	-

Neco Williams D 89 0 0.07 0.06 ok 1 1.2 6.8 59.3 39 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 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.006` `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=0.9864` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.2558 -> 1.2745 totalCross: 6.1286 -> 6.1101 interceptionWon: 1.0569 -> 1.0479 totalShots: 1.1601 -> 1.1544
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Erling Haaland', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1001 -> 0.0695 expected_assists: 0.128 -> 0.092
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 80.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0671` `goal_rate=0.1548` `scorer_weight=0.0869`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0879` `assist_rate=0.0269` `provider_weight=0.0736`	-

Ola Aina D 78 0 0.01 0.01 34% 1 0.5 6.8 51.5 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0046, quality 0.594)	`market_value_eur=16399999` `quality_factor=0.5942` `boost_factor=1.0046` `reference_quality=0.505` `history_matches=24` `history_shrink=0.1724`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0134)	`blend_weight=0.0134` `history_matches=24` `season_overlap_discount=1.0` `per90_to_match_factor=0.8722` `prior_reliability=0.12` `competition=Premier League`	totalCross: 1.7844 -> 1.7995 wonTackle: 1.4219 -> 1.4093 fouls: 0.7515 -> 0.7609 interceptionWon: 1.1149 -> 1.1064 onTargetScoringAttempt: 0.0742 -> 0.0799 totalShots: 0.5761 -> 0.5817
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Erling Haaland', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0586 -> 0.0421
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 79.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0098` `goal_rate=0.0` `scorer_weight=0.0078`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0412` `assist_rate=0.0` `provider_weight=0.0337`	-

Morgan Gibbs-White M 89 0 0.16 0.29 45% 2 1.8 7.1 61.7 38 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 1.0112, quality 0.878)	`market_value_eur=76000000` `quality_factor=0.8781` `boost_factor=1.0112` `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=0.9912` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 3.8645 -> 3.8482
`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': 'Elliot Anderson', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.412, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9445, 'skill_edge': -0.0058, 'height_edge': -0.032, 'attacker_skill': 0.8855, 'defender_skill': 0.8984, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Elliot Anderson', 'market_value': 109000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8984}], 'xg_override': 0.2309}	aerialWon: 0.3993 -> 0.8 totalShots: 2.1948 -> 2.073 shotOffTarget: 1.4163 -> 1.3377 onTargetScoringAttempt: 0.7779 -> 0.7347 bigChanceMissed: 0.3845 -> 0.3632 goals: 0.2735 -> 0.2583 expectedGoals: 0.2445 -> 0.2309 expectedGoalsOnTarget: 0.1835 -> 0.1733
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2309 -> 0.1603 expected_assists: 0.1793 -> 0.1288
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 83.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1481` `goal_rate=0.2583` `scorer_weight=0.1759`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1209` `assist_rate=0.1876` `provider_weight=0.1335`	-

James McAtee M 86 0 0.05 0.03 79% 1 0.6 7.0 31.1 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 1.0066, quality 0.629)	`market_value_eur=19800000` `quality_factor=0.6291` `boost_factor=1.0066` `reference_quality=0.505` `history_matches=23` `history_shrink=0.1786`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0139)	`blend_weight=0.0139` `history_matches=23` `season_overlap_discount=1.0` `per90_to_match_factor=0.9569` `prior_reliability=0.12` `competition=Premier League`	totalShots: 1.31 -> 1.2918 fouls: 1.0172 -> 1.003 interceptionWon: 1.0154 -> 1.0013 totalCross: 3.1018 -> 3.1104 wasFouled: 1.6649 -> 1.6713 wonTackle: 1.4361 -> 1.4309
`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': 'Abdukodir Khusanov', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run', 'duel_win_rate': 0.303, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8576, 'skill_edge': -0.0729, 'height_edge': -0.024, 'attacker_skill': 0.7044, 'defender_skill': 0.8663, 'attacker_role': 'LWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Abdukodir Khusanov', 'market_value': 47000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8663}], 'xg_override': 0.0677}	aerialWon: 0.3329 -> 1.1 totalShots: 1.3056 -> 1.1197 shotOffTarget: 0.9915 -> 0.8503 onTargetScoringAttempt: 0.3141 -> 0.2694 goals: 0.1013 -> 0.0869 expectedGoals: 0.0789 -> 0.0677
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0677 -> 0.047 expected_assists: 0.161 -> 0.1157
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 73.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0459` `goal_rate=0.0869` `scorer_weight=0.0547`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1093` `assist_rate=0.0907` `provider_weight=0.0926`	-

Xaver Schlager M 79 0 0.03 0.03 ok 1 0.9 6.9 44.8 14 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0070, quality 0.570)	`market_value_eur=14200000` `quality_factor=0.5704` `boost_factor=1.007` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0186)	`blend_weight=0.0186` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.8817` `prior_reliability=0.08` `competition=Premier League`	fouls: 1.3902 -> 1.3644 interceptionWon: 1.2399 -> 1.2169 wonTackle: 1.9064 -> 1.8983 totalCross: 0.353 -> 0.3601 totalShots: 1.1076 -> 1.1145
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Marc Guéhi', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run', 'duel_win_rate': 0.251, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.781, 'skill_edge': -0.117, 'height_edge': -0.032, 'attacker_skill': 0.6339, 'defender_skill': 0.8938, 'attacker_role': 'RWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Marc Guéhi', 'market_value': 71000000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.8938}], 'xg_override': 0.0444}	aerialWon: 0.5381 -> 0.9 totalShots: 1.1145 -> 0.8704 shotOffTarget: 0.8856 -> 0.6917 onTargetScoringAttempt: 0.2179 -> 0.1702 bigChanceMissed: 0.0921 -> 0.0719 goals: 0.0766 -> 0.0598 expectedGoals: 0.0568 -> 0.0444
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0444 -> 0.0308 expected_assists: 0.054 -> 0.0388
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 78.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0303` `goal_rate=0.0598` `scorer_weight=0.0358`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0381` `assist_rate=0.0527` `provider_weight=0.0383`	-

Daniel Muñoz M 82 0 0.07 0.06 ok 1 0.7 6.8 51.3 32 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 1.0055, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0055` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Elliot Anderson', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.369, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8804, 'skill_edge': -0.0973, 'height_edge': 0.016, 'attacker_skill': 0.6821, 'defender_skill': 0.8984, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Elliot Anderson', 'market_value': 109000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8984}], 'xg_override': 0.0976}	aerialWon: 1.9688 -> 1.1 totalShots: 1.1292 -> 0.9942 shotOffTarget: 0.7593 -> 0.6685 onTargetScoringAttempt: 0.3699 -> 0.3257 bigChanceMissed: 0.3313 -> 0.2917 goals: 0.1166 -> 0.1027 expectedGoals: 0.1109 -> 0.0976 expectedGoalsOnTarget: 0.0853 -> 0.0751
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0976 -> 0.0677 expected_assists: 0.0921 -> 0.0662
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 82.0)	`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=0.0655` `goal_rate=0.1027` `scorer_weight=0.07`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0641` `assist_rate=0.1027` `provider_weight=0.0711`	-

Dan Ndoye F 69 0 0.16 0.08 114% 2 0.8 6.8 33.7 34 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 1.0095, quality 0.746)	`market_value_eur=34000000` `quality_factor=0.7455` `boost_factor=1.0095` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0080)	`blend_weight=0.008` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.7612` `prior_reliability=0.0933` `competition=Premier League`	fouls: 0.7663 -> 0.7732 totalCross: 0.7986 -> 0.7922
`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': 'Elliot Anderson, Matheus Nunes', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.225, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9338, 'skill_edge': -0.057, 'height_edge': 0.012, 'attacker_skill': 0.7455, 'defender_skill': 0.8723, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Elliot Anderson', 'market_value': 109000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8984}, {'player': 'Matheus Nunes', 'market_value': 43000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8462}], 'xg_override': 0.2354}	totalShots: 2.1009 -> 1.9618 shotOffTarget: 1.3998 -> 1.3071 onTargetScoringAttempt: 0.7011 -> 0.6547 bigChanceMissed: 0.6101 -> 0.5697 expectedGoals: 0.2521 -> 0.2354 goals: 0.2316 -> 0.2163 expectedGoalsOnTarget: 0.1768 -> 0.1651
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2354 -> 0.1634 expected_assists: 0.0684 -> 0.0492
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 77.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1507` `goal_rate=0.2163` `scorer_weight=0.1525`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.048` `assist_rate=0.0051` `provider_weight=0.0394`	-

Liam Delap F 79 0 0.19 0.19 ok 2 1.4 6.7 52.9 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0095, quality 0.764)	`market_value_eur=37000000` `quality_factor=0.7641` `boost_factor=1.0095` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0016)	`blend_weight=0.0016` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.88` `prior_reliability=0.02` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Matheus Nunes, Rúben Dias', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9391, 'skill_edge': -0.0434, 'height_edge': 0.002, 'attacker_skill': 0.7641, 'defender_skill': 0.8606, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Matheus Nunes', 'market_value': 43000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8462}, {'player': 'Rúben Dias', 'market_value': 55000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8751}], 'xg_override': 0.2672}	totalShots: 2.2508 -> 2.1137 shotOffTarget: 1.5302 -> 1.437 onTargetScoringAttempt: 0.718 -> 0.6743 bigChanceMissed: 0.4986 -> 0.4682 expectedGoals: 0.2845 -> 0.2672 goals: 0.2722 -> 0.2556 expectedGoalsOnTarget: 0.1002 -> 0.0941
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2672 -> 0.1855 expected_assists: 0.0632 -> 0.0454
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 77.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1693` `goal_rate=0.2556` `scorer_weight=0.1787`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0444` `assist_rate=0.0` `provider_weight=0.0363`	-

Igor Jesus F 80 0 0.17 0.15 ok 2 1.4 6.8 55.6 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 1.0058, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0058` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.8877` `prior_reliability=0.1333` `competition=Premier League`	fouls: 1.5816 -> 1.5875 totalShots: 2.0962 -> 2.1016
`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': 'Elliot Anderson, Matheus Nunes', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8649, 'skill_edge': -0.0839, 'height_edge': -0.008, 'attacker_skill': 0.6858, 'defender_skill': 0.8723, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Elliot Anderson', 'market_value': 109000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8984}, {'player': 'Matheus Nunes', 'market_value': 43000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8462}], 'xg_override': 0.2446}	totalShots: 2.1016 -> 1.8177 shotOffTarget: 1.3054 -> 1.129 onTargetScoringAttempt: 0.7917 -> 0.6847 goals: 0.3096 -> 0.2678 expectedGoals: 0.2828 -> 0.2446 expectedGoalsOnTarget: 0.212 -> 0.1834 bigChanceMissed: 0.2081 -> 0.18
`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 1.07 (squad xG sum 1.5371, xG scale 0.6942, xA scale 0.7186, team xA 0.69 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.067` `squad_xg_sum=1.5371` `squad_xa_sum=0.9652` `team_expected_assists=0.6935` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2446 -> 0.1698 expected_assists: 0.0567 -> 0.0407
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 77.0)	`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=0.1562` `goal_rate=0.2678` `scorer_weight=0.1832`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0399` `assist_rate=0.1175` `provider_weight=0.0509`	-

Team totals 0 1.07 16 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
John Victor	G	4.4m	11.0%	Market-value substitute prior
Ousmane Diomande	D	15.0m	36.4%	Market-value substitute prior
Jair	D	14.6m	34.3%	Market-value substitute prior
Ibrahim Sangaré	M	22.8m	32.3%	Market-value substitute prior
Nicolás Domínguez	M	10.6m	70.1%	Market-value substitute prior
Callum Hudson Odoi	F	26.3m	60.3%	Market-value substitute prior

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

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

Gianluigi Donnarumma G 90 0 0.00 - n/a 0.0 7.0 60.1 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 1.0095, quality 0.809)	`market_value_eur=46000000` `quality_factor=0.8089` `boost_factor=1.0095` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.8616 -> 2.8538
`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': 'Liam Delap, Igor Jesus', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2421}`	-
`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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	shots_faced: 11.8 -> 10.1 expected_saves: 2.89 -> 2.47 high_pressure_saves: 0.99 -> 0.85
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 89.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.9743`	-
`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=1.3335`	-

Marc Guéhi D 84 0 0.09 0.14 32% 1 0.8 7.1 60.0 33 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0115, quality 0.872)	`market_value_eur=71000000` `quality_factor=0.8721` `boost_factor=1.0115` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9282` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.5519 -> 0.5637 interceptionWon: 0.8281 -> 0.8332
`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': 'Xaver Schlager', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run'}`	-
`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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0765 -> 0.092 expected_assists: 0.0506 -> 0.06
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 85.0)	`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=0.0879` `goal_rate=0.0698` `scorer_weight=0.0871`	-
`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=0.0582` `assist_rate=0.1191` `provider_weight=0.075`	-

Rúben Dias D 89 0 0.06 0.03 134% 1 0.3 7.0 46.0 26 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 1.0126, quality 0.840)	`market_value_eur=55000000` `quality_factor=0.8399` `boost_factor=1.0126` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0108)	`blend_weight=0.0108` `history_matches=35` `season_overlap_discount=1.0` `per90_to_match_factor=0.9884` `prior_reliability=0.1333` `competition=Premier League`	fouls: 1.4023 -> 1.3871
`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': 'Liam Delap', '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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0492 -> 0.0592 expected_assists: 0.0604 -> 0.0716
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 87.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0575` `goal_rate=0.0112` `scorer_weight=0.0474`	-
`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=0.0691` `assist_rate=0.0` `provider_weight=0.0573`	-

Matheus Nunes D 86 0 0.03 0.01 310% 0 0.1 6.9 52.5 33 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0097, quality 0.796)	`market_value_eur=43000000` `quality_factor=0.7957` `boost_factor=1.0097` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0019)	`blend_weight=0.0019` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9574` `prior_reliability=0.0267` `competition=Premier League`	totalCross: 1.1608 -> 1.1678
`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': 'Liam Delap', '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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0492 -> 0.0583
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 83.0)	`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=0.0287` `goal_rate=0.0005` `scorer_weight=0.0233`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0566` `assist_rate=0.0421` `provider_weight=0.0541`	-

Abdukodir Khusanov D 89 0 0.04 0.02 69% 1 0.3 7.0 47.8 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0144, quality 0.813)	`market_value_eur=47000000` `quality_factor=0.8129` `boost_factor=1.0144` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0135)	`blend_weight=0.0135` `history_matches=27` `season_overlap_discount=1.0` `per90_to_match_factor=0.9877` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 0.907 -> 0.9281 fouls: 1.2869 -> 1.2695 totalShots: 0.5421 -> 0.5348 wasFouled: 0.4795 -> 0.473
`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': 'James McAtee', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run'}`	-
`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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0334 -> 0.0402 expected_assists: 0.0423 -> 0.0502
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 82.0)	`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=0.0394` `goal_rate=0.0` `scorer_weight=0.0322`	-
`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=0.049` `assist_rate=0.0` `provider_weight=0.0402`	-

Elliot Anderson M 87 0 0.06 0.04 48% 1 1.0 7.3 63.1 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 1.0113, quality 0.896)	`market_value_eur=109000000` `quality_factor=0.8957` `boost_factor=1.0113` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0067)	`blend_weight=0.0067` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=0.967` `prior_reliability=0.1067` `competition=Premier League`	interceptionWon: 1.3574 -> 1.3685 wasFouled: 2.9373 -> 2.9298 wonTackle: 1.384 -> 1.3909
`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': 'Dan Ndoye, Igor Jesus, Morgan Gibbs-White', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.049 -> 0.0589 expected_assists: 0.1684 -> 0.1997
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 84.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0572` `goal_rate=0.059` `scorer_weight=0.0648`	-
`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=0.181` `assist_rate=0.0844` `provider_weight=0.1598`	-

Enzo Fernández M 83 0 0.19 0.18 ok 2 1.5 7.2 60.2 31 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 1.0120, quality 0.897)	`market_value_eur=116000000` `quality_factor=0.897` `boost_factor=1.012` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`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': 'Murillo', 'matchup_zone': 'LW vs CB', 'duel_win_rate': 0.411, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.987, 'skill_edge': 0.0152, 'height_edge': -0.024, 'attacker_skill': 0.897, 'defender_skill': 0.8633, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Murillo', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}], 'xg_override': 0.1615}`	aerialWon: 0.6552 -> 1.0 totalShots: 1.5751 -> 1.5546 shotOffTarget: 0.9926 -> 0.9797 onTargetScoringAttempt: 0.5825 -> 0.5749
`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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1615 -> 0.1943 expected_assists: 0.1981 -> 0.2349
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 86.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1766` `goal_rate=0.1712` `scorer_weight=0.2032`	-
`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=0.2094` `assist_rate=0.1265` `provider_weight=0.1879`	-

Rayan Cherki M 73 0 0.25 0.14 83% 3 1.6 7.2 59.7 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 1.0128, quality 0.898)	`market_value_eur=120000000` `quality_factor=0.8975` `boost_factor=1.0128` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0057)	`blend_weight=0.0057` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.8119` `prior_reliability=0.08` `competition=Premier League`	totalCross: 2.2817 -> 2.2917 fouls: 0.9869 -> 0.9966 onTargetScoringAttempt: 0.649 -> 0.6567 goalAssist: 0.2049 -> 0.2114 goals: 0.2675 -> 0.2736 wasFouled: 0.8826 -> 0.8776
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Morgan Gibbs-White', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.446, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.0378, 'skill_edge': 0.0057, 'height_edge': 0.02, 'attacker_skill': 0.8982, 'defender_skill': 0.8855, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Morgan Gibbs-White', 'market_value': 76000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.8855}], 'xg_override': 0.2076}	aerialWon: 0.0 -> 0.9 totalShots: 2.3609 -> 2.4501 shotOffTarget: 1.7042 -> 1.7686 onTargetScoringAttempt: 0.6567 -> 0.6815 expectedGoalsOnTarget: 0.4314 -> 0.4477 goals: 0.2736 -> 0.2839 expectedGoals: 0.2 -> 0.2076 bigChanceMissed: 0.1986 -> 0.2061
`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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2076 -> 0.2497 expected_assists: 0.2018 -> 0.2391
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 86.0)	`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=0.221` `goal_rate=0.2839` `scorer_weight=0.3121`	-
`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=0.2127` `assist_rate=0.2114` `provider_weight=0.2482`	-

Phil Foden M 74 0 0.16 0.12 ok 2 0.8 7.0 50.5 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0117, quality 0.857)	`market_value_eur=62000000` `quality_factor=0.8569` `boost_factor=1.0117` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.8271` `prior_reliability=0.1267` `competition=Premier League`	totalCross: 3.771 -> 3.7843 fouls: 0.5569 -> 0.5638 goalAssist: 0.1872 -> 0.1935 wasFouled: 1.0474 -> 1.0537 totalShots: 1.5436 -> 1.5494 onTargetScoringAttempt: 0.5485 -> 0.5435
`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': 'Murillo', 'matchup_zone': 'RW vs CB', 'duel_win_rate': 0.369, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9252, 'skill_edge': -0.0029, 'height_edge': -0.048, 'attacker_skill': 0.8569, 'defender_skill': 0.8633, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Murillo', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}], 'xg_override': 0.1313}`	aerialWon: 0.5132 -> 0.8 totalShots: 1.5494 -> 1.4335 shotOffTarget: 0.9951 -> 0.9207 onTargetScoringAttempt: 0.5435 -> 0.5028 bigChanceMissed: 0.2781 -> 0.2573 goals: 0.1671 -> 0.1546 expectedGoalsOnTarget: 0.1574 -> 0.1456 expectedGoals: 0.1419 -> 0.1313
`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 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1313 -> 0.158 expected_assists: 0.1959 -> 0.2323
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 84.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1462` `goal_rate=0.1546` `scorer_weight=0.1783`	-
`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=0.2073` `assist_rate=0.1935` `provider_weight=0.23`	-

Ayyoub Bouaddi M 79 0 0.05 0.00 2950% 1 0.1 6.9 26.2 13 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 1.0581, quality 0.893)	`market_value_eur=98000000` `quality_factor=0.8926` `boost_factor=1.0581` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0022)	`blend_weight=0.0022` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.8727` `prior_reliability=0.0067` `competition=Premier League`	interceptionWon: 0.3914 -> 0.4096
`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 McAtee', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0456 -> 0.0549 expected_assists: 0.0485 -> 0.0575
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 80.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0534` `goal_rate=0.0645` `scorer_weight=0.0658`	-
`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=0.0559` `assist_rate=0.0827` `provider_weight=0.0719`	-

Erling Haaland F 88 1 0.75 0.49 53% 4 2.9 7.2 58.5 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0121, quality 0.900)	`market_value_eur=240000000` `quality_factor=0.9` `boost_factor=1.0121` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9803` `prior_reliability=0.1333` `competition=Premier League`	totalShots: 3.2489 -> 3.2635 onTargetScoringAttempt: 1.4086 -> 1.4178 fouls: 0.6535 -> 0.6477
`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': 'Murillo, Neco Williams', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.285, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 1.1245, 'skill_edge': 0.0367, 'height_edge': 0.048, 'attacker_skill': 0.9, 'defender_skill': 0.8184, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Murillo', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}, {'player': 'Neco Williams', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}], 'xg_override': 0.6263}	totalShots: 3.2635 -> 3.6698 shotOffTarget: 1.8402 -> 2.0693 onTargetScoringAttempt: 1.4178 -> 1.5943 expectedGoalsOnTarget: 0.8394 -> 0.9439 bigChanceMissed: 0.7053 -> 0.7931 goals: 0.6349 -> 0.7139 expectedGoals: 0.557 -> 0.6263
`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`	goals: 1.0 -> 0
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.78 (squad xG sum 1.4796, xG scale 1.2030, xA scale 1.1857, team xA 1.42 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.78` `squad_xg_sum=1.4796` `squad_xa_sum=1.201` `team_expected_assists=1.424` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.6263 -> 0.7535 expected_assists: 0.0526 -> 0.0624
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 91.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.5293` `goal_rate=0.7139` `scorer_weight=0.8511`	-
`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=0.0605` `assist_rate=0.0572` `provider_weight=0.0652`	-

Team totals 1 1.78 17 7.1

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Gerónimo Rulli	G	4.5m	11.3%	Market-value substitute prior
Nico O'Reilly	D	15.3m	25.3%	Market-value substitute prior
Joško Gvardiol	D	15.3m	25.2%	Market-value substitute prior
Mateo Kovačić	M	22.1m	69.9%	Market-value substitute prior
Floyd Samba	M	22.0m	49.9%	Market-value substitute prior
Antoine Semenyo	F	27.1m	37.0%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~52% possession expected (Morgan Gibbs-White vs Rayan Cherki). Total antagonist xG — Home: 1.19, Away: 1.13. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 48.5% / 51.5%, dominance ratio 0.43, key duel: Morgan Gibbs-White vs Rayan Cherki

Liam Delap xG 0.27Dan Ndoye xG 0.24Igor Jesus xG 0.24Enzo Fernández xG 0.16Rayan Cherki xG 0.21Phil Foden xG 0.13

Summary

Antagonist matchup analysis for Forest vs Man City. Most likely scoreline: 0-1. Lambdas derived from 7 home and 4 away individual player duels. Head-to-head: Forest 2W-2D-6L vs Man City over 10 meetings.

Tactical parity between 3-4-2-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~52% possession expected (Morgan Gibbs-White vs Rayan Cherki). Total antagonist xG — Home: 1.19, Away: 1.13. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Fulham vs Newcastle

Premier League · 20261107 · 4-2-3-1 vs 4-2-3-1

Predicted 1-0Winner: FulhamWinning H 1-0 (9.3%)Winning A 0-1 (7.8%)Confidence 0.66λ home/away 1.51 / 1.27Most-likely P 9.3%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Fulham vs Newcastle. 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 1.353, Away 1.192). Final calibrated Poisson lambdas: Home 1.513, Away 1.268 (most likely score 1-0).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (7 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.35 / 1.19 Final λ (H/A) 1.51 / 1.27

FBref Team Priors: Fulham (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 1.379) vs Newcastle United (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 1.379) | Blend Weight: 0.192

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Fulham	Newcastle
League position	15.00	12.00
Points per game	1.14	1.37
Attack index	0.93	1.04
Defense (concede) index	1.11	1.00
Form multiplier	0.99	1.01
Standing λ multiplier	1.01	1.02

Lambda decomposition (how the goal rates were built)

Stage	Fulham λ	Newcastle λ
FBref Squad Prior E[λ] (weight 0.192)	1.379	1.379
Pre-competitive-floor	1.445	1.189
Pre-calibration (Micro-duels)	1.353	1.192
Final λ	1.513	1.268

competition calibration scale 1.056competition 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	12.0%
1-0	9.3%
2-1	9.0%
0-1	7.8%
1-2	7.5%

Home win	42.9%
Draw	25.4%
Away win	31.8%
Over 2.5	52.6%
BTTS yes	56.1%

Pregame fair line — favorite Fulham (42.9%), fair total 2.78, fair spread 0.24

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.

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

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

Bernd Leno G 90 0 0.00 - n/a 0.0 7.0 58.6 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 0.9989, quality 0.468)	`market_value_eur=5500000` `quality_factor=0.4683` `boost_factor=0.9989` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0083)	`blend_weight=0.0083` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Harvey Barnes, Joe Willock', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.1922}`	-
`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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	shots_faced: 11.3 -> 12.0 expected_saves: 2.76 -> 2.93 high_pressure_saves: 0.95 -> 1.01
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 79.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.4297`	-
`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=1.0368`	-

Calvin Bassey D 90 0 0.07 0.04 70% 1 0.5 7.0 53.6 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0070, quality 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.007` `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=1.0` `prior_reliability=0.1333` `competition=Premier League`	fouls: 1.2751 -> 1.2675
`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': 'Harvey Barnes', '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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.0529 -> 0.0682
`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=0.0659` `goal_rate=0.0046` `scorer_weight=0.0546`	-
`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=0.0197` `assist_rate=0.0` `provider_weight=0.0159`	-

Antonee Robinson D 87 0 0.09 0.04 129% 1 0.3 6.8 50.4 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0070, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.007` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0118)	`blend_weight=0.0118` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.9716` `prior_reliability=0.1267` `competition=Premier League`	fouls: 1.4061 -> 1.3896 wonTackle: 1.6098 -> 1.6209 interceptionWon: 1.1706 -> 1.1628
`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': 'Sean Steur', '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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.0702 -> 0.0905 expected_assists: 0.0732 -> 0.0944
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 80.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0865` `goal_rate=0.0389` `scorer_weight=0.0724`	-
`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=0.0901` `assist_rate=0.0` `provider_weight=0.0755`	-

David Affengruber D 89 0 0.08 0.03 147% 1 0.5 7.0 56.9 35 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0032, quality 0.612)	`market_value_eur=18100000` `quality_factor=0.612` `boost_factor=1.0032` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Joe Willock', '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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.0588 -> 0.0758 expected_assists: 0.0296 -> 0.0382
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 76.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.073` `goal_rate=0.0141` `scorer_weight=0.0606`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0375` `assist_rate=0.0131` `provider_weight=0.0306`	-

Timothy Castagne D 87 0 0.08 0.05 57% 1 0.4 6.8 50.4 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 0.9996, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9996` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0086)	`blend_weight=0.0086` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9632` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 0.5543 -> 0.569 fouls: 1.1517 -> 1.1661
`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': 'Harvey Barnes', '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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.0613 -> 0.079 expected_assists: 0.1336 -> 0.1723
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 75.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.076` `goal_rate=0.0` `scorer_weight=0.0632`	-
`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=0.1583` `assist_rate=0.053` `provider_weight=0.1378`	-

Alex Iwobi M 81 0 0.21 0.08 174% 2 1.1 7.2 52.6 37 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0047, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0047` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0101)	`blend_weight=0.0101` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.8991` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 4.7632 -> 4.7379 totalShots: 1.9683 -> 1.953 interceptionWon: 0.5573 -> 0.5653 onTargetScoringAttempt: 0.6321 -> 0.6257
`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': 'Lewis Hall', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.39, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8678, 'skill_edge': -0.1059, 'height_edge': 0.016, 'attacker_skill': 0.6408, 'defender_skill': 0.8762, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Lewis Hall', 'market_value': 52000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8762}], 'xg_override': 0.1657}	aerialWon: 0.0602 -> 1.1 totalShots: 1.9619 -> 1.7026 shotOffTarget: 1.3362 -> 1.1596 onTargetScoringAttempt: 0.6257 -> 0.543 bigChanceMissed: 0.3515 -> 0.305 goals: 0.2091 -> 0.1815 expectedGoals: 0.191 -> 0.1657 expectedGoalsOnTarget: 0.1098 -> 0.0953
`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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.1657 -> 0.2137 expected_assists: 0.1983 -> 0.2557
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 80.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1924` `goal_rate=0.1815` `scorer_weight=0.2293`	-
`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=0.2256` `assist_rate=0.1265` `provider_weight=0.2046`	-

Josh King M 78 0 0.22 0.10 115% 2 1.0 6.9 50.8 31 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 1.0092, quality 0.786)	`market_value_eur=41000000` `quality_factor=0.7859` `boost_factor=1.0092` `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': 'Lewis Miley, Joelinton', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.214, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.9615, 'skill_edge': 0.0338, 'height_edge': -0.06, 'attacker_skill': 0.7964, 'defender_skill': 0.7213, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Lewis Miley', 'market_value': 32000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7679}, {'player': 'Joelinton', 'market_value': 21000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.6747}], 'xg_override': 0.1703}	aerialWon: 0.2495 -> 0.8 totalShots: 2.0531 -> 1.9741 shotOffTarget: 1.2874 -> 1.2378 onTargetScoringAttempt: 0.7657 -> 0.7362 bigChanceMissed: 0.2746 -> 0.264 goals: 0.2107 -> 0.2026 expectedGoalsOnTarget: 0.1808 -> 0.1738 expectedGoals: 0.1771 -> 0.1703
`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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.1703 -> 0.2196 expected_assists: 0.1434 -> 0.1849
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 78.0)	`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=0.1972` `goal_rate=0.2026` `scorer_weight=0.2518`	-
`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=0.1688` `assist_rate=0.1352` `provider_weight=0.1771`	-

Shea Charles M 86 0 0.10 0.05 102% 1 0.5 7.0 45.0 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 1.0175, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0175` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0077)	`blend_weight=0.0077` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.96` `prior_reliability=0.0333` `competition=Premier League`	totalShots: 0.9258 -> 0.9471 totalCross: 0.1172 -> 0.1311 wasFouled: 1.2587 -> 1.249 wonTackle: 1.1237 -> 1.1299 fouls: 0.6776 -> 0.6724
`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': 'Lewis Miley', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.395, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9637, 'skill_edge': -0.0287, 'height_edge': 0.004, 'attacker_skill': 0.704, 'defender_skill': 0.7679, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Lewis Miley', 'market_value': 32000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7679}], 'xg_override': 0.0768}	aerialWon: 1.5107 -> 1.3 totalShots: 0.9471 -> 0.9127 shotOffTarget: 0.6662 -> 0.642 onTargetScoringAttempt: 0.2576 -> 0.2482 bigChanceMissed: 0.2247 -> 0.2165
`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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.0768 -> 0.099 expected_assists: 0.0829 -> 0.1069
`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=0.0943` `goal_rate=0.0711` `scorer_weight=0.0945`	-
`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=0.1014` `assist_rate=0.0582` `provider_weight=0.087`	-

Sander Berge M 85 0 0.08 0.04 116% 1 0.5 7.0 54.7 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 1.0055, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0055` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0075)	`blend_weight=0.0075` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.943` `prior_reliability=0.1133` `competition=Premier League`	wonTackle: 0.8683 -> 0.8618
`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': 'Lewis Miley', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.427, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.0108, 'skill_edge': -0.0207, 'height_edge': 0.028, 'attacker_skill': 0.7219, 'defender_skill': 0.7679, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Lewis Miley', 'market_value': 32000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7679}], 'xg_override': 0.0606}	aerialWon: 0.9748 -> 1.4 totalShots: 0.5474 -> 0.5533
`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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.0606 -> 0.0781 expected_assists: 0.0558 -> 0.072
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 79.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0751` `goal_rate=0.0593` `scorer_weight=0.0772`	-
`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=0.0695` `assist_rate=0.0571` `provider_weight=0.0729`	-

Emile Smith Rowe M 73 0 0.13 0.08 60% 1 0.7 6.8 50.6 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 1.0026, quality 0.586)	`market_value_eur=15600000` `quality_factor=0.5857` `boost_factor=1.0026` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0009)	`blend_weight=0.0009` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.8114` `prior_reliability=0.0133` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Fabian Schär', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.524, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0652, 'skill_edge': 0.0603, 'height_edge': -0.016, 'attacker_skill': 0.5857, 'defender_skill': 0.4516, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Fabian Schär', 'market_value': 2900000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.4516}], 'xg_override': 0.0984}	aerialWon: 0.2709 -> 1.1 totalShots: 1.0901 -> 1.1612 shotOffTarget: 0.7542 -> 0.8034 onTargetScoringAttempt: 0.332 -> 0.3536 bigChanceMissed: 0.1887 -> 0.201 expectedGoals: 0.0924 -> 0.0984 goals: 0.0908 -> 0.0967
`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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.0984 -> 0.1269 expected_assists: 0.0416 -> 0.0536
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 77.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1192` `goal_rate=0.0967` `scorer_weight=0.1254`	-
`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=0.0522` `assist_rate=0.0645` `provider_weight=0.067`	-

Gonzalo García F 82 1 0.35 0.24 48% 2 1.2 6.7 50.7 34 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 1.0086, quality 0.758)	`market_value_eur=36000000` `quality_factor=0.7581` `boost_factor=1.0086` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0098)	`blend_weight=0.0098` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9096` `prior_reliability=0.1333` `competition=Premier League`	fouls: 0.8761 -> 0.8854 totalShots: 1.9645 -> 1.972 wasFouled: 0.262 -> 0.2684
`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': 'Sven Botman, Malick Thiaw', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8863, 'skill_edge': -0.0314, 'height_edge': -0.046, 'attacker_skill': 0.7581, 'defender_skill': 0.8279, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Sven Botman', 'market_value': 33000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8002}, {'player': 'Malick Thiaw', 'market_value': 46000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8555}], 'xg_override': 0.2728}	totalShots: 1.972 -> 1.7478 shotOffTarget: 1.2588 -> 1.1157 bigChanceMissed: 0.7427 -> 0.6583 onTargetScoringAttempt: 0.7032 -> 0.6232 expectedGoals: 0.3078 -> 0.2728 goals: 0.2412 -> 0.2138 expectedGoalsOnTarget: 0.1307 -> 0.1158
`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 1.51 (squad xG sum 1.1733, xG scale 1.2895, xA scale 1.2895, team xA 1.19 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.513` `squad_xg_sum=1.1733` `squad_xa_sum=0.9264` `team_expected_assists=1.1946` `team_xa_to_xg_ratio=0.7896`	expected_goals: 0.2728 -> 0.3519 expected_assists: 0.0568 -> 0.0732
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 78.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2966` `goal_rate=0.2138` `scorer_weight=0.2876`	-
`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=0.0706` `assist_rate=0.0` `provider_weight=0.0586`	-

Team totals 1 1.51 15 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Benjamin Lecomte	G	4.4m	10.9%	Market-value substitute prior
Ryan Sessegnon	D	18.0m	61.8%	Market-value substitute prior
Joachim Andersen	D	14.2m	23.0%	Market-value substitute prior
Hugo Larsson	M	22.9m	54.0%	Market-value substitute prior
Manuel Ángel Morán	M	22.1m	50.2%	Market-value substitute prior
Oscar Bobb	F	26.3m	35.5%	Market-value substitute prior

Newcastle — 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

Nick Pope G 90 0 0.00 0.01 100% 0.0 6.9 31.8 30 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9968, quality 0.437)	`market_value_eur=2900000` `quality_factor=0.4374` `boost_factor=0.9968` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gonzalo García, Josh King', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.3528}`	-
`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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	shots_faced: 12.9 -> 14.4 expected_saves: 3.16 -> 3.53 high_pressure_saves: 1.08 -> 1.21
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 78.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3379`	-
`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=0.9545`	-

Lewis Hall D 89 0 0.05 0.03 83% 1 0.6 6.9 52.4 33 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0114, quality 0.831)	`market_value_eur=52000000` `quality_factor=0.8309` `boost_factor=1.0114` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0101)	`blend_weight=0.0101` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9861` `prior_reliability=0.1333` `competition=Premier League`	fouls: 0.7338 -> 0.7413 wasFouled: 1.7102 -> 1.7029 wonTackle: 1.2852 -> 1.2921
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Alex Iwobi', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.0356 -> 0.0471 expected_assists: 0.0971 -> 0.1284
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 83.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.046` `goal_rate=0.1032` `scorer_weight=0.0589`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1205` `assist_rate=0.0684` `provider_weight=0.1033`	-

Sven Botman D 89 0 0.07 0.06 ok 1 0.6 7.1 47.9 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 1.0095, quality 0.739)	`market_value_eur=33000000` `quality_factor=0.7389` `boost_factor=1.0095` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0117)	`blend_weight=0.0117` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.9912` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.1257 -> 1.1125 wonTackle: 0.6733 -> 0.6654
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gonzalo García', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.0495 -> 0.0654 expected_assists: 0.0381 -> 0.0504
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0633` `goal_rate=0.1396` `scorer_weight=0.0818`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0492` `assist_rate=0.0` `provider_weight=0.0403`	-

Malick Thiaw D 90 0 0.07 0.10 34% 0 0.5 6.8 55.9 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 1.0095, quality 0.809)	`market_value_eur=46000000` `quality_factor=0.8089` `boost_factor=1.0095` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9983` `prior_reliability=0.1333` `competition=Premier League`	wasFouled: 0.3308 -> 0.3413 interceptionWon: 0.9739 -> 0.9651
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gonzalo García', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.0521 -> 0.0689 expected_assists: 0.0247 -> 0.0327
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 81.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0666` `goal_rate=0.0131` `scorer_weight=0.0551`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0322` `assist_rate=0.0` `provider_weight=0.0262`	-

Fabian Schär D 88 0 0.12 0.02 501% 1 0.1 7.0 18.2 16 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 0.9958, quality 0.437)	`market_value_eur=2900000` `quality_factor=0.4374` `boost_factor=0.9958` `reference_quality=0.505` `history_matches=19` `history_shrink=0.2083`	-
`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': 'Emile Smith Rowe', '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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.0915 -> 0.121 expected_assists: 0.0315 -> 0.0416
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 81.0)	`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=0.114` `goal_rate=0.0` `scorer_weight=0.0968`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0407` `assist_rate=0.0` `provider_weight=0.0333`	-

Lewis Miley M 82 0 0.05 0.03 55% 0 0.2 6.9 50.6 22 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 0.732)	`market_value_eur=32000000` `quality_factor=0.732` `boost_factor=1.0097` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0111)	`blend_weight=0.0111` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=0.9129` `prior_reliability=0.12` `competition=Premier League`	totalCross: 1.8178 -> 1.7975 wasFouled: 0.1804 -> 0.1897 wonTackle: 1.1649 -> 1.1576
`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': 'Shea Charles', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.445, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0363, 'skill_edge': 0.0287, 'height_edge': -0.004, 'attacker_skill': 0.7679, 'defender_skill': 0.704, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Shea Charles', 'market_value': 24000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.704}], 'xg_override': 0.038}	aerialWon: 1.7925 -> 1.2 totalShots: 0.394 -> 0.4083 shotOffTarget: 0.266 -> 0.2757
`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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.038 -> 0.0502 expected_assists: 0.0765 -> 0.1011
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 77.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.049` `goal_rate=0.0469` `scorer_weight=0.0553`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0962` `assist_rate=0.0742` `provider_weight=0.0993`	-

Nico González M 77 0 0.06 0.01 613% 1 0.2 7.1 34.4 28 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0138, quality 0.837)	`market_value_eur=54000000` `quality_factor=0.837` `boost_factor=1.0138` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`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': 'Shea Charles, Sander Berge', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.275, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 1.052, 'skill_edge': 0.0594, 'height_edge': -0.024, 'attacker_skill': 0.8449, 'defender_skill': 0.713, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Shea Charles', 'market_value': 24000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.704}, {'player': 'Sander Berge', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}], 'xg_override': 0.0434}	aerialWon: 1.1459 -> 1.2 totalShots: 0.5823 -> 0.6126 shotOffTarget: 0.4404 -> 0.4633 onTargetScoringAttempt: 0.1419 -> 0.1493
`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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.0434 -> 0.0574 expected_assists: 0.0741 -> 0.098
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 81.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0558` `goal_rate=0.0468` `scorer_weight=0.0595`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0934` `assist_rate=0.0665` `provider_weight=0.092`	-

Joelinton M 86 0 0.10 0.07 47% 1 1.0 6.8 48.1 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 1.0058, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0058` `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': 'Shea Charles', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.395, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.963, 'skill_edge': -0.0132, 'height_edge': -0.012, 'attacker_skill': 0.6747, 'defender_skill': 0.704, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Shea Charles', 'market_value': 24000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.704}], 'xg_override': 0.0787}	aerialWon: 3.3331 -> 1.2 totalShots: 1.0305 -> 0.9924 shotOffTarget: 0.7464 -> 0.7188 onTargetScoringAttempt: 0.2841 -> 0.2736
`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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.0787 -> 0.1041 expected_assists: 0.0516 -> 0.0682
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 80.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0989` `goal_rate=0.0815` `scorer_weight=0.1064`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0659` `assist_rate=0.0732` `provider_weight=0.0827`	-

Joe Willock M 72 0 0.21 0.07 204% 2 0.9 6.9 44.2 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 1.0046, quality 0.618)	`market_value_eur=18700000` `quality_factor=0.6181` `boost_factor=1.0046` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0070)	`blend_weight=0.007` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.8034` `prior_reliability=0.08` `competition=Premier League`	fouls: 0.7199 -> 0.7384 wasFouled: 1.1597 -> 1.1516 totalCross: 0.4003 -> 0.4069 totalShots: 1.888 -> 1.8941
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'David Affengruber', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.454, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9619, 'skill_edge': -0.0299, 'height_edge': 0.004, 'attacker_skill': 0.6181, 'defender_skill': 0.6846, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'David Affengruber', 'market_value': 18100000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.6846}], 'xg_override': 0.1568}	aerialWon: 0.3971 -> 1.2 totalShots: 1.8941 -> 1.8219 shotOffTarget: 1.2799 -> 1.2311 onTargetScoringAttempt: 0.6087 -> 0.5855 expectedGoals: 0.163 -> 0.1568 goals: 0.157 -> 0.151
`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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.1568 -> 0.2073 expected_assists: 0.1083 -> 0.1432
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 76.0)	`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=0.1872` `goal_rate=0.151` `scorer_weight=0.2015`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1334` `assist_rate=0.1131` `provider_weight=0.1475`	-

Sean Steur M 74 0 0.04 - n/a 0 0.0 6.8 30.7 13 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 1.0185, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0185` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0157)	`blend_weight=0.0157` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.8189` `prior_reliability=0.0533` `competition=Premier League`	wonTackle: 0.7714 -> 0.7593 totalShots: 0.4913 -> 0.4836
`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': 'Antonee Robinson', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.432, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.9295, 'skill_edge': -0.048, 'height_edge': 0.0, 'attacker_skill': 0.6408, 'defender_skill': 0.7474, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Antonee Robinson', 'market_value': 24000000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.7474}], 'xg_override': 0.0327}	aerialWon: 0.0 -> 1.1 totalShots: 0.489 -> 0.4545 shotOffTarget: 0.352 -> 0.3272 onTargetScoringAttempt: 0.137 -> 0.1273
`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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.0327 -> 0.0432 expected_assists: 0.0345 -> 0.0456
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 72.0)	`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=0.0423` `goal_rate=0.0554` `scorer_weight=0.054`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0446` `assist_rate=0.0533` `provider_weight=0.0557`	-

Harvey Barnes F 85 0 0.35 0.15 138% 3 1.7 6.9 57.9 39 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0079, quality 0.770)	`market_value_eur=38000000` `quality_factor=0.7699` `boost_factor=1.0079` `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=0.943` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 3.6855 -> 3.6658 totalShots: 2.2026 -> 2.1918 onTargetScoringAttempt: 0.7315 -> 0.7252
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Calvin Bassey, Timothy Castagne', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.238, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0566, 'skill_edge': 0.0545, 'height_edge': -0.016, 'attacker_skill': 0.7699, 'defender_skill': 0.6488, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Calvin Bassey', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Timothy Castagne', 'market_value': 7600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.524}], 'xg_override': 0.2652}	totalShots: 2.1962 -> 2.3205 shotOffTarget: 1.471 -> 1.5543 onTargetScoringAttempt: 0.7252 -> 0.7662 goals: 0.2942 -> 0.3109 expectedGoals: 0.251 -> 0.2652 expectedGoalsOnTarget: 0.2049 -> 0.2165 bigChanceMissed: 0.1296 -> 0.1369
`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 1.27 (squad xG sum 0.9590, xG scale 1.3222, xA scale 1.3222, team xA 0.96 = 0.75 x lambda)	`scoreline_reset=true` `team_lambda=1.268` `squad_xg_sum=0.959` `squad_xa_sum=0.7236` `team_expected_assists=0.9567` `team_xa_to_xg_ratio=0.7545`	expected_goals: 0.2652 -> 0.3507 expected_assists: 0.1131 -> 0.1496
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 80.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.2958` `goal_rate=0.3109` `scorer_weight=0.4016`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1389` `assist_rate=0.2277` `provider_weight=0.187`	-

Team totals 0 1.27 11 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Lukáš Horníček	G	5.3m	15.1%	Market-value substitute prior
Tino Livramento	D	15.0m	36.4%	Market-value substitute prior
Amar Dedić	D	14.7m	23.9%	Market-value substitute prior
Aladji Bamba	M	18.5m	71.0%	Market-value substitute prior
Mason Miley	M	22.0m	49.9%	Market-value substitute prior
Matías Fernández-Pardo	F	26.9m	63.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Josh King vs Nico González will be the pivotal duel. Total antagonist xG — Home: 0.84, Away: 0.61. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.7% / 50.3%, dominance ratio 0.49, key duel: Josh King vs Nico González

Alex Iwobi xG 0.17Emile Smith Rowe xG 0.10Josh King xG 0.17Joe Willock xG 0.16Sean Steur xG 0.03Nico González xG 0.04

Summary

Antagonist matchup analysis for Fulham vs Newcastle. Most likely scoreline: 1-0. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Fulham 3W-0D-7L vs Newcastle 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 — Josh King vs Nico González will be the pivotal duel. Total antagonist xG — Home: 0.84, Away: 0.61. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Valencia vs Real Madrid

LaLiga · 20261107 · 4-4-2 vs 4-2-3-1

Predicted 0-2Winner: Real MadridWinning H 2-1 (4.1%)Winning A 0-2 (10.5%)Confidence 0.73λ home/away 0.94 / 2.26Most-likely P 10.5%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Valencia vs Real Madrid. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-4-2 vs 4-2-3-1 (duel lambdas: Home 0.859, Away 2.463). Final calibrated Poisson lambdas: Home 0.935, Away 2.256 (most likely score 0-2).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.86 / 2.46 Final λ (H/A) 0.94 / 2.26

FBref Team Priors: Valencia (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.822) vs Real Madrid (Gls/90: 3.0, GA/90: 3.33 → E[λ]: 0.733) | Blend Weight: 0.228

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Valencia	Real Madrid
League position	19.00	3.00
Points per game	0.89	2.01
Attack index	0.76	1.30
Defense (concede) index	0.85	1.06
Form multiplier	0.95	1.05
Standing λ multiplier	0.83	1.15

Lambda decomposition (how the goal rates were built)

Stage	Valencia λ	Real Madrid λ
FBref Squad Prior E[λ] (weight 0.228)	0.822	0.733
Pre-mismatch	1.077	2.678
Pre-calibration (Micro-duels)	0.859	2.463
Final λ	0.935	2.256

competition calibration scale 0.85competition observed total goals 2.984quality gap applied Truemismatch score pressure applied Truecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
0-2	10.5%
1-2	9.8%
0-1	9.2%
1-1	8.7%
0-3	7.9%

Home win	14.2%
Draw	18.7%
Away win	67.2%
Over 2.5	61.8%
BTTS yes	54.4%

Pregame fair line — favorite Real Madrid (67.2%), fair total 3.19, fair spread -1.32

Projected players vs season baseline

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

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

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

Stole Dimitrievski G 90 0 0.00 - n/a 0.0 6.9 63.1 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 0.9971, quality 0.437)	`market_value_eur=2100000` `quality_factor=0.4374` `boost_factor=0.9971` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0186)	`blend_weight=0.0186` `history_matches=30` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kylian Mbappé, Arda Güler', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 2.4627}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	shots_faced: 23.4 -> 21.4 expected_saves: 5.73 -> 5.23 high_pressure_saves: 1.97 -> 1.8
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.0185`	-
`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=0.7168`	-

José Copete D 88 0 0.04 0.02 99% 1 0.6 6.8 50.6 9 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9972, quality 0.456)	`market_value_eur=4500000` `quality_factor=0.456` `boost_factor=0.9972` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`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': 'Thiago Pitarch', '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 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.0313 -> 0.0377 expected_assists: 0.0277 -> 0.0333
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 77.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.037` `goal_rate=0.0` `scorer_weight=0.0302`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0328` `assist_rate=0.0` `provider_weight=0.0266`	-

José Luis Gayà D 83 0 0.05 0.03 91% 1 0.4 6.8 55.0 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 0.9983, quality 0.454)	`market_value_eur=4300000` `quality_factor=0.4535` `boost_factor=0.9983` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0038)	`blend_weight=0.0038` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9267` `prior_reliability=0.0533` `competition=La Liga`	wasFouled: 0.8235 -> 0.8292
`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': 'Arda Güler', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.0453 -> 0.0545 expected_assists: 0.0598 -> 0.072
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 80.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.053` `goal_rate=0.0052` `scorer_weight=0.0436`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0695` `assist_rate=0.0313` `provider_weight=0.0576`	-

Mouctar Diakhaby D 73 0 0.04 0.01 300% 0 0.2 6.7 37.1 10 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 0.9944, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9944` `reference_quality=0.505` `history_matches=13` `history_shrink=0.2778`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0301)	`blend_weight=0.0301` `history_matches=13` `season_overlap_discount=1.0` `per90_to_match_factor=0.8106` `prior_reliability=0.1667` `competition=La Liga`	interceptionWon: 1.0322 -> 1.0499 wonTackle: 0.6469 -> 0.6372 fouls: 0.6461 -> 0.6364
`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': 'Kylian Mbappé', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.033 -> 0.0397
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 76.0)	`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=0.0389` `goal_rate=0.0342` `scorer_weight=0.0403`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0089` `assist_rate=0.0` `provider_weight=0.0078`	-

César Tárrega D 83 0 0.05 0.02 133% 1 0.4 6.9 49.6 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 1.0003, quality 0.514)	`market_value_eur=9300000` `quality_factor=0.5142` `boost_factor=1.0003` `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=0.9186` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.2556 -> 1.2416 wonTackle: 0.9316 -> 0.9405
`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': 'Kylian Mbappé', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.0425 -> 0.0512
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 75.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0499` `goal_rate=0.0` `scorer_weight=0.041`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.007` `assist_rate=0.0` `provider_weight=0.0063`	-

Javier Guerra M 81 0 0.16 0.10 57% 1 1.1 6.9 59.0 37 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0053, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0053` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0115)	`blend_weight=0.0115` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=0.901` `prior_reliability=0.18` `competition=La Liga`	fouls: 1.1056 -> 1.0929 totalShots: 1.6755 -> 1.668 onTargetScoringAttempt: 0.5347 -> 0.5286
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Álvaro Carreras', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel', 'duel_win_rate': 0.388, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8943, 'skill_edge': -0.0759, 'height_edge': 0.004, 'attacker_skill': 0.7091, 'defender_skill': 0.8778, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Álvaro Carreras', 'market_value': 53000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8778}], 'xg_override': 0.1348}	aerialWon: 0.618 -> 1.2 totalShots: 1.6694 -> 1.4929 shotOffTarget: 1.1408 -> 1.0202 onTargetScoringAttempt: 0.5286 -> 0.4727 bigChanceMissed: 0.2735 -> 0.2446 goals: 0.1959 -> 0.1752 expectedGoals: 0.1507 -> 0.1348 expectedGoalsOnTarget: 0.1226 -> 0.1096
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.1348 -> 0.1621 expected_assists: 0.126 -> 0.1517
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 82.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1496` `goal_rate=0.1752` `scorer_weight=0.1975`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1408` `assist_rate=0.1375` `provider_weight=0.1616`	-

Pepelu M 85 0 0.05 0.10 50% 0 0.5 6.9 53.2 40 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9995, quality 0.490)	`market_value_eur=7300000` `quality_factor=0.4903` `boost_factor=0.9995` `reference_quality=0.505` `history_matches=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': 'Federico Valverde', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.289, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7629, 'skill_edge': -0.1773, 'height_edge': 0.016, 'attacker_skill': 0.5, 'defender_skill': 0.894, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Federico Valverde', 'market_value': 87000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.894}], 'xg_override': 0.0406}	aerialWon: 0.5012 -> 1.2 totalShots: 0.5882 -> 0.4487 shotOffTarget: 0.4094 -> 0.3123 onTargetScoringAttempt: 0.1788 -> 0.1364 expectedGoalsOnTarget: 0.1549 -> 0.1182 goals: 0.0642 -> 0.049 expectedGoals: 0.0532 -> 0.0406
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.0406 -> 0.0489 expected_assists: 0.0391 -> 0.0471
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 76.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0477` `goal_rate=0.049` `scorer_weight=0.0534`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.046` `assist_rate=0.0516` `provider_weight=0.0537`	-

Guido Rodríguez M 86 0 0.04 0.04 ok 0 0.6 7.0 59.4 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9973, quality 0.445)	`market_value_eur=3600000` `quality_factor=0.4449` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=29` `history_shrink=0.1471`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0127)	`blend_weight=0.0127` `history_matches=29` `season_overlap_discount=1.0` `per90_to_match_factor=0.9508` `prior_reliability=0.1333` `competition=La Liga`	interceptionWon: 1.3963 -> 1.4088
`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': 'Federico Valverde', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.266, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7297, 'skill_edge': -0.1999, 'height_edge': 0.016, 'attacker_skill': 0.4498, 'defender_skill': 0.894, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Federico Valverde', 'market_value': 87000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.894}], 'xg_override': 0.0303}	totalShots: 0.5557 -> 0.4055 shotOffTarget: 0.3968 -> 0.2895 aerialWon: 1.2549 -> 1.2 onTargetScoringAttempt: 0.1589 -> 0.1159 goals: 0.0561 -> 0.0409 expectedGoals: 0.0415 -> 0.0303 expectedGoalsOnTarget: 0.0325 -> 0.0237
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.0303 -> 0.0365 expected_assists: 0.0355 -> 0.0427
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 78.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0358` `goal_rate=0.0409` `scorer_weight=0.0413`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0418` `assist_rate=0.0471` `provider_weight=0.0485`	-

Filip Ugrinić M 74 0 0.05 0.04 38% 1 0.7 6.8 63.3 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9988, quality 0.471)	`market_value_eur=5700000` `quality_factor=0.4708` `boost_factor=0.9988` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0114)	`blend_weight=0.0114` `history_matches=37` `season_overlap_discount=1.0` `per90_to_match_factor=0.8234` `prior_reliability=0.1467` `competition=La Liga`	wasFouled: 1.0776 -> 1.0994 totalShots: 0.6637 -> 0.6822 totalCross: 2.8281 -> 2.8427 onTargetScoringAttempt: 0.205 -> 0.2114
`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': 'Raúl Asencio', 'matchup_zone': 'Right Mid vs Left Back — Wide Channel', 'duel_win_rate': 0.381, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8844, 'skill_edge': -0.0826, 'height_edge': 0.004, 'attacker_skill': 0.4785, 'defender_skill': 0.6621, 'attacker_role': 'RM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Raúl Asencio', 'market_value': 16300000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.6621}], 'xg_override': 0.044}	aerialWon: 0.3855 -> 1.2 totalShots: 0.6822 -> 0.6033 shotOffTarget: 0.4587 -> 0.4057 onTargetScoringAttempt: 0.2114 -> 0.187 goals: 0.058 -> 0.0513 expectedGoals: 0.0497 -> 0.044
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.044 -> 0.053 expected_assists: 0.0845 -> 0.1017
`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=0.0516` `goal_rate=0.0513` `scorer_weight=0.0571`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0967` `assist_rate=0.07` `provider_weight=0.0907`	-

Arnaut Danjuma F 83 0 0.11 0.08 37% 1 1.0 6.9 52.8 35 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=2800000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9237` `prior_reliability=0.1267` `competition=La Liga`	totalShots: 1.5769 -> 1.5943 wasFouled: 0.7597 -> 0.7705 fouls: 0.7168 -> 0.7236
`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': 'Dean Huijsen, Ibrahima Konaté', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.6245, 'skill_edge': -0.1954, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.8717, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Dean Huijsen', 'market_value': 66000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8879}, {'player': 'Ibrahima Konaté', 'market_value': 46000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8555}], 'xg_override': 0.0906}	totalShots: 1.5943 -> 0.9956 shotOffTarget: 0.9717 -> 0.6068 onTargetScoringAttempt: 0.6088 -> 0.3802 bigChanceMissed: 0.4115 -> 0.257 goals: 0.1932 -> 0.1207 expectedGoals: 0.1451 -> 0.0906 expectedGoalsOnTarget: 0.107 -> 0.0668
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.0906 -> 0.1091 expected_assists: 0.0938 -> 0.1129
`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=0.1034` `goal_rate=0.1207` `scorer_weight=0.1325`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1068` `assist_rate=0.032` `provider_weight=0.0903`	-

Diego López F 72 0 0.12 0.03 335% 1 0.4 6.8 49.6 23 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0005, quality 0.518)	`market_value_eur=9600000` `quality_factor=0.5177` `boost_factor=1.0005` `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': 'Dean Huijsen, Ibrahima Konaté', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.6777, 'skill_edge': -0.1593, 'height_edge': -0.06, 'attacker_skill': 0.5177, 'defender_skill': 0.8717, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Dean Huijsen', 'market_value': 66000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8879}, {'player': 'Ibrahima Konaté', 'market_value': 46000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8555}], 'xg_override': 0.0961}	totalShots: 1.4313 -> 0.97 shotOffTarget: 0.996 -> 0.675 onTargetScoringAttempt: 0.4353 -> 0.295 goals: 0.1757 -> 0.1191 expectedGoals: 0.1418 -> 0.0961 bigChanceMissed: 0.096 -> 0.0651 expectedGoalsOnTarget: 0.0893 -> 0.0605
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.94 (squad xG sum 0.7768, xG scale 1.2036, xA scale 1.2036, team xA 0.72 = 0.77 x lambda)	`scoreline_reset=true` `team_lambda=0.935` `squad_xg_sum=0.7768` `squad_xa_sum=0.5964` `team_expected_assists=0.7179` `team_xa_to_xg_ratio=0.7678`	expected_goals: 0.0961 -> 0.1157 expected_assists: 0.0851 -> 0.1024
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 77.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1093` `goal_rate=0.1191` `scorer_weight=0.1339`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0973` `assist_rate=0.1327` `provider_weight=0.128`	-

Team totals 0 0.94 10 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Kayne van Oevelen	G	4.5m	11.1%	Market-value substitute prior
Arnau Martínez	D	13.9m	22.5%	Market-value substitute prior
Justin De Haas	D	13.8m	22.2%	Market-value substitute prior
Harvey Elliott	M	22.7m	53.1%	Market-value substitute prior
Aaron Mayol	M	22.1m	50.3%	Market-value substitute prior
Hugo Duro	F	22.6m	59.8%	Market-value substitute prior

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

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

Thibaut Courtois G 90 0 0.00 - n/a 0.0 7.0 61.6 26 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 1.0022, quality 0.574)	`market_value_eur=14500000` `quality_factor=0.5737` `boost_factor=1.0022` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0141)	`blend_weight=0.0141` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.7796 -> 2.7639
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Javier Guerra, Diego López', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.8591}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	shots_faced: 8.2 -> 8.9 expected_saves: 2.01 -> 2.18 high_pressure_saves: 0.69 -> 0.75
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 90.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=2.5662`	-
`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=1.4244`	-

Ibrahima Konaté D 89 0 0.04 0.02 80% 0 0.3 6.9 59.9 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 1.0091, quality 0.809)	`market_value_eur=46000000` `quality_factor=0.8089` `boost_factor=1.0091` `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=0.9923` `prior_reliability=0.1333` `competition=La Liga`	wonTackle: 0.8508 -> 0.8606 fouls: 1.0684 -> 1.0634
`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': 'Arnaut Danjuma', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0323 -> 0.0428 expected_assists: 0.0095 -> 0.0154
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 84.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0419` `goal_rate=0.0042` `scorer_weight=0.0342`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0153` `assist_rate=0.0` `provider_weight=0.0129`	-

Raúl Asencio D 87 0 0.07 0.04 85% 0 0.3 7.0 37.0 21 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0047, quality 0.593)	`market_value_eur=16300000` `quality_factor=0.5932` `boost_factor=1.0047` `reference_quality=0.505` `history_matches=23` `history_shrink=0.1786`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Filip Ugrinić', 'matchup_zone': 'Right Mid vs Left Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0531 -> 0.0704 expected_assists: 0.0363 -> 0.059
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 80.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.068` `goal_rate=0.0692` `scorer_weight=0.0814`	-
`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=0.0573` `assist_rate=0.0` `provider_weight=0.0472`	-

Dean Huijsen D 84 0 0.09 0.05 73% 1 0.5 7.1 59.0 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0131, quality 0.864)	`market_value_eur=66000000` `quality_factor=0.8644` `boost_factor=1.0131` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0159)	`blend_weight=0.0159` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.9372` `prior_reliability=0.2` `competition=La Liga`	totalShots: 0.497 -> 0.504
`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': 'Arnaut Danjuma', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0644 -> 0.0854 expected_assists: 0.0283 -> 0.046
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 81.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0819` `goal_rate=0.0206` `scorer_weight=0.0683`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.045` `assist_rate=0.0126` `provider_weight=0.0368`	-

Álvaro Carreras D 77 0 0.05 0.02 240% 0 0.1 6.9 41.1 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0130, quality 0.834)	`market_value_eur=53000000` `quality_factor=0.834` `boost_factor=1.013` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0068)	`blend_weight=0.0068` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.8523` `prior_reliability=0.08` `competition=La Liga`	-
`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': 'Javier Guerra', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0388 -> 0.0515 expected_assists: 0.0771 -> 0.1253
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 81.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0502` `goal_rate=0.163` `scorer_weight=0.0644`	-
`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=0.1178` `assist_rate=0.1207` `provider_weight=0.1566`	-

Federico Valverde M 81 0 0.10 0.07 34% 1 1.2 7.0 68.6 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0119, quality 0.887)	`market_value_eur=87000000` `quality_factor=0.8873` `boost_factor=1.0119` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0126)	`blend_weight=0.0126` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.8953` `prior_reliability=0.1867` `competition=La Liga`	wonTackle: 0.6509 -> 0.6629 wasFouled: 0.4778 -> 0.4718 interceptionWon: 1.3539 -> 1.3489
`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': 'Pepelu', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.561, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2371, 'skill_edge': 0.1773, 'height_edge': -0.016, 'attacker_skill': 0.894, 'defender_skill': 0.5, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pepelu', 'market_value': 7300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5}], 'xg_override': 0.0726}	aerialWon: 0.6714 -> 1.1 totalShots: 0.7386 -> 0.9137 shotOffTarget: 0.4916 -> 0.6082 onTargetScoringAttempt: 0.2453 -> 0.3035 expectedGoals: 0.0587 -> 0.0726 goals: 0.0574 -> 0.071 expectedGoalsOnTarget: 0.0508 -> 0.0628
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0726 -> 0.0963 expected_assists: 0.0666 -> 0.1082
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 87.0)	`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=0.0918` `goal_rate=0.071` `scorer_weight=0.095`	-
`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=0.1026` `assist_rate=0.0742` `provider_weight=0.1153`	-

Aurélien Tchouaméni M 83 0 0.09 0.06 46% 1 1.2 7.0 61.5 27 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 1.0126, quality 0.875)	`market_value_eur=73000000` `quality_factor=0.8747` `boost_factor=1.0126` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pepelu', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.586, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2733, 'skill_edge': 0.1739, 'height_edge': 0.012, 'attacker_skill': 0.8865, 'defender_skill': 0.5, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Pepelu', 'market_value': 7300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5}], 'xg_override': 0.066}	totalShots: 0.837 -> 1.0658 shotOffTarget: 0.6569 -> 0.8364 aerialWon: 1.2886 -> 1.2 onTargetScoringAttempt: 0.1801 -> 0.2293 expectedGoals: 0.0518 -> 0.066 goals: 0.0489 -> 0.0623 bigChanceMissed: 0.04 -> 0.0509 expectedGoalsOnTarget: 0.0347 -> 0.0442
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.066 -> 0.0875 expected_assists: 0.041 -> 0.0666
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 84.0)	`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=0.0838` `goal_rate=0.0623` `scorer_weight=0.0847`	-
`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=0.0644` `assist_rate=0.0579` `provider_weight=0.079`	-

Jude Bellingham M 83 0 0.24 0.15 53% 2 1.5 7.1 64.9 27 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0138, quality 0.899)	`market_value_eur=151000000` `quality_factor=0.8995` `boost_factor=1.0138` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0136)	`blend_weight=0.0136` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9241` `prior_reliability=0.18` `competition=La Liga`	totalShots: 1.6784 -> 1.693 wasFouled: 3.3107 -> 3.2983 onTargetScoringAttempt: 0.5848 -> 0.5956 goalAssist: 0.1251 -> 0.1327 goals: 0.1529 -> 0.1601 interceptionWon: 0.5104 -> 0.5035
`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': 'Pepelu', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.612, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.282, 'skill_edge': 0.1798, 'height_edge': 0.012, 'attacker_skill': 0.8996, 'defender_skill': 0.5, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Pepelu', 'market_value': 7300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5}], 'xg_override': 0.1778}`	aerialWon: 0.6141 -> 1.2 totalShots: 1.693 -> 2.1704 shotOffTarget: 1.0936 -> 1.402 onTargetScoringAttempt: 0.5956 -> 0.7636 expectedGoalsOnTarget: 0.1937 -> 0.2483 goals: 0.1601 -> 0.2052 expectedGoals: 0.1387 -> 0.1778 bigChanceMissed: 0.1282 -> 0.1644
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1778 -> 0.2358 expected_assists: 0.1378 -> 0.224
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 90.0)	`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=0.2101` `goal_rate=0.2052` `scorer_weight=0.2642`	-
`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=0.2007` `assist_rate=0.1327` `provider_weight=0.2179`	-

Arda Güler M 74 0 0.31 0.11 168% 3 1.3 7.2 65.8 28 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0121, quality 0.892)	`market_value_eur=97000000` `quality_factor=0.8922` `boost_factor=1.0121` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0072)	`blend_weight=0.0072` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.821` `prior_reliability=0.1067` `competition=La Liga`	wonTackle: 0.7624 -> 0.768 wasFouled: 1.771 -> 1.7656
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'José Luis Gayà', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.683, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.2987, 'skill_edge': 0.1872, 'height_edge': 0.016, 'attacker_skill': 0.8922, 'defender_skill': 0.4762, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'José Luis Gayà', 'market_value': 4300000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4762}], 'xg_override': 0.2317}	aerialWon: 0.2778 -> 0.9 totalShots: 1.9559 -> 2.5401 shotOffTarget: 1.2365 -> 1.6058 onTargetScoringAttempt: 0.7194 -> 0.9343 goals: 0.1788 -> 0.2322 expectedGoals: 0.1784 -> 0.2317 expectedGoalsOnTarget: 0.1261 -> 0.1638 bigChanceMissed: 0.106 -> 0.1377
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2317 -> 0.3073 expected_assists: 0.1926 -> 0.313
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 83.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2646` `goal_rate=0.2322` `scorer_weight=0.3079`	-
`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=0.2688` `assist_rate=0.1794` `provider_weight=0.296`	-

Thiago Pitarch M 74 0 0.08 0.02 321% 1 0.3 6.9 28.3 23 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0108, quality 0.613)	`market_value_eur=18200000` `quality_factor=0.613` `boost_factor=1.0108` `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': 'José Copete', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.496, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0235, 'skill_edge': 0.06, 'height_edge': -0.044, 'attacker_skill': 0.613, 'defender_skill': 0.4797, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'José Copete', 'market_value': 4500000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.4797}], 'xg_override': 0.0566}	aerialWon: 0.2752 -> 1.0 totalShots: 0.7416 -> 0.759 shotOffTarget: 0.5247 -> 0.537 onTargetScoringAttempt: 0.2169 -> 0.222
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0566 -> 0.0751 expected_assists: 0.0543 -> 0.0883
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 70.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0723` `goal_rate=0.0495` `scorer_weight=0.0701`	-
`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=0.0845` `assist_rate=0.0643` `provider_weight=0.0968`	-

Kylian Mbappé F 89 2 1.12 0.76 49% 5 4.1 7.8 63.4 27 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0129, quality 0.900)	`market_value_eur=212000000` `quality_factor=0.9` `boost_factor=1.0129` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0141)	`blend_weight=0.0141` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.9837` `prior_reliability=0.2` `competition=La Liga`	totalShots: 3.8724 -> 3.9289 onTargetScoringAttempt: 2.0425 -> 2.0785 totalOffside: 1.3559 -> 1.3414 wasFouled: 1.7267 -> 1.7162 totalCross: 1.1122 -> 1.1058 fouls: 0.6096 -> 0.6149
`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': 'Mouctar Diakhaby, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.333, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1952, 'skill_edge': 0.1828, 'height_edge': -0.05, 'attacker_skill': 0.9, 'defender_skill': 0.4938, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mouctar Diakhaby', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.8472}	totalShots: 3.9289 -> 4.6958 onTargetScoringAttempt: 2.0785 -> 2.4842 shotOffTarget: 1.8299 -> 2.1871 bigChanceMissed: 1.2781 -> 1.5276 expectedGoalsOnTarget: 1.1434 -> 1.3666 goals: 0.9862 -> 1.1787 expectedGoals: 0.7088 -> 0.8472
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	goals: 1.0 -> 0
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.26 (squad xG sum 1.7009, xG scale 1.3264, xA scale 1.6253, team xA 1.47 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.256` `squad_xg_sum=1.7009` `squad_xa_sum=0.9022` `team_expected_assists=1.4664` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.8472 -> 1.1238 expected_assists: 0.1804 -> 0.2932
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 91.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=2` `goal_probability=0.675` `goal_rate=1.1787` `scorer_weight=1.4047`	-
`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=0.2541` `assist_rate=0.1516` `provider_weight=0.2566`	-

Team totals 2 2.26 15 7.1

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Andriy Lunin	G	4.8m	12.7%	Market-value substitute prior
Trent Alexander-Arnold	D	12.9m	44.3%	Market-value substitute prior
Marc Cucurella	D	26.6m	50.8%	Market-value substitute prior
Eduardo Camavinga	M	17.2m	59.4%	Market-value substitute prior
Bernardo Silva	M	17.9m	45.2%	Market-value substitute prior
Vinícius Júnior	F	27.1m	37.1%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~54% possession expected (Javier Guerra vs Jude Bellingham). Total antagonist xG — Home: 0.44, Away: 1.45. Home danger zone: Left Mid vs Right Back — Wide Channel. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 46.3% / 53.7%, dominance ratio 0.38, key duel: Javier Guerra vs Jude Bellingham

Arnaut Danjuma xG 0.09Diego López xG 0.10Javier Guerra xG 0.13Arda Güler xG 0.23Thiago Pitarch xG 0.06Jude Bellingham xG 0.18

Summary

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

Tactical parity between 4-4-2 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~54% possession expected (Javier Guerra vs Jude Bellingham). Total antagonist xG — Home: 0.44, Away: 1.45. Home danger zone: Left Mid vs Right Back — Wide Channel. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Málaga vs Racing Club

LaLiga · 20261107 · 4-1-4-1 vs 4-2-3-1

Predicted 1-0Winner: MálagaWinning H 1-0 (10.1%)Winning A 0-1 (8.3%)Confidence 0.65λ home/away 1.45 / 1.20Most-likely P 10.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Málaga vs Racing Club. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-1-4-1 vs 4-2-3-1 (duel lambdas: Home 1.024, Away 0.941). Final calibrated Poisson lambdas: Home 1.453, Away 1.200 (most likely score 1-0).

Home Starters 11/11 XGBoost (0 FBref) Away Starters 11/11 XGBoost (0 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.02 / 0.94 Final λ (H/A) 1.45 / 1.20

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	Málaga	Racing Club
League position	20.00	15.00
Points per game	0.78	1.20
Attack index	0.79	1.00
Defense (concede) index	1.33	1.18
Form multiplier	0.98	1.02
Standing λ multiplier	1.01	1.07

Lambda decomposition (how the goal rates were built)

Stage	Málaga λ	Racing Club λ
Pre-competitive-floor	1.031	0.934
Pre-calibration (Micro-duels)	1.024	0.941
Final λ	1.453	1.200

competition calibration scale 1.35competition observed total goals 2.984quality gap applied Falsemismatch score pressure applied Falsecompetitive underdog floor applied Falsestage discount 1.0

Scoreline distribution & markets

Top 5 scorelines	P
1-1	12.4%
1-0	10.1%
2-1	8.9%
0-1	8.3%
2-0	7.4%

Home win	42.8%
Draw	26.1%
Away win	31.1%
Over 2.5	49.5%
BTTS yes	53.6%

Pregame fair line — favorite Málaga (42.8%), fair total 2.65, fair spread 0.25

Projected players vs season baseline

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

Málaga — projected line vs season baseline (4-1-4-1)

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

Alfonso Herrero G 90 0 0.00 - n/a 0.0 7.0 58.7 13 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9937, quality 0.437)	`market_value_eur=420000` `quality_factor=0.4374` `boost_factor=0.9937` `reference_quality=0.505` `history_matches=11` `history_shrink=0.3125`	-
`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': 'Maguette Gueye, Iñigo Vicente', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.9405}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	shots_faced: 8.9 -> 11.4 expected_saves: 2.17 -> 2.79 high_pressure_saves: 0.75 -> 0.96
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 75.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=1.608`	-
`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=1.0769`	-

Ángel Recio D 90 0 0.04 0.01 212% 0 0.6 6.9 55.7 12 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9932, quality 0.437)	`market_value_eur=1000000` `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': 'Iñigo Vicente', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0173 -> 0.0423 expected_assists: 0.0093 -> 0.0171
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 65.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0414` `goal_rate=0.0` `scorer_weight=0.0338`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.017` `assist_rate=0.0` `provider_weight=0.0144`	-

Rafa Garrido D 89 0 0.02 0.01 272% 0 0.2 6.8 56.2 13 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 0.9937, quality 0.437)	`market_value_eur=1400000` `quality_factor=0.4374` `boost_factor=0.9937` `reference_quality=0.505` `history_matches=11` `history_shrink=0.3125`	-
`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': 'André Almeida', '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 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0088 -> 0.0215 expected_assists: 0.0224 -> 0.0412
`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_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=0.0213` `goal_rate=0.0` `scorer_weight=0.0183`	-
`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=0.0404` `assist_rate=0.114` `provider_weight=0.0515`	-

Einar Galilea D 84 0 0.00 - n/a 0 0.0 6.9 41.5 13 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.437)	`market_value_eur=365000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Iván Martín', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 69.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0096` `assist_rate=0.0` `provider_weight=0.0087`	-

Fernando Calero D 85 0 0.07 0.02 208% 0 0.3 6.8 53.0 23 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 0.9972, quality 0.437)	`market_value_eur=2100000` `quality_factor=0.4374` `boost_factor=0.9972` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Iñigo Vicente', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0297 -> 0.0727 expected_assists: 0.0106 -> 0.0195
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 81.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_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=0.0701` `goal_rate=0.0` `scorer_weight=0.0582`	-
`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=0.0193` `assist_rate=0.0` `provider_weight=0.0161`	-

Carlos Dotor M 80 0 0.16 0.05 231% 1 0.5 6.9 58.1 13 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 0.9932, quality 0.437)	`market_value_eur=1200000` `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': 'Matteo Prati', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.396, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9647, 'skill_edge': -0.016, 'height_edge': -0.008, 'attacker_skill': 0.4374, 'defender_skill': 0.473, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Matteo Prati', 'market_value': 5000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.473}], 'xg_override': 0.0654}	aerialWon: 0.172 -> 1.1 totalShots: 0.8191 -> 0.7902 shotOffTarget: 0.5641 -> 0.5442 onTargetScoringAttempt: 0.2549 -> 0.2459
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0654 -> 0.16 expected_assists: 0.0666 -> 0.1226
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 85.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_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=0.1479` `goal_rate=0.0637` `scorer_weight=0.1576`	-
`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=0.1154` `assist_rate=0.0823` `provider_weight=0.1391`	-

Pablo Martínez M 82 1 0.25 0.06 343% 2 0.9 6.9 61.4 27 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9974, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `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': 'Pablo Ramón', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel', 'duel_win_rate': 0.446, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9801, 'skill_edge': 0.0025, 'height_edge': -0.016, 'attacker_skill': 0.4429, 'defender_skill': 0.4374, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Pablo Ramón', 'market_value': 1500000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.1032}	aerialWon: 0.3454 -> 1.1 totalShots: 1.6341 -> 1.6016 shotOffTarget: 1.1722 -> 1.1489 onTargetScoringAttempt: 0.4618 -> 0.4526
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1032 -> 0.2525 expected_assists: 0.1702 -> 0.3134
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 82.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2231` `goal_rate=0.1404` `scorer_weight=0.3138`	-
`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=0.269` `assist_rate=0.1299` `provider_weight=0.256`	-

Dani Lorenzo M 82 0 0.15 0.03 394% 1 0.3 6.9 56.9 12 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 0.9932, quality 0.437)	`market_value_eur=2300000` `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': 'Jorge Salinas', 'matchup_zone': 'Right Mid vs Left Back — Wide Channel', 'duel_win_rate': 0.391, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8979, 'skill_edge': -0.0494, 'height_edge': -0.02, 'attacker_skill': 0.4374, 'defender_skill': 0.5473, 'attacker_role': 'RM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Jorge Salinas', 'market_value': 8500000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.5473}], 'xg_override': 0.0598}	aerialWon: 0.148 -> 0.9 totalShots: 0.6896 -> 0.6192 shotOffTarget: 0.4473 -> 0.4016 onTargetScoringAttempt: 0.2422 -> 0.2175 bigChanceMissed: 0.104 -> 0.0934 goals: 0.0773 -> 0.0694 expectedGoals: 0.0666 -> 0.0598
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0598 -> 0.1463 expected_assists: 0.0804 -> 0.1481
`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=0.1361` `goal_rate=0.0694` `scorer_weight=0.1591`	-
`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=0.1377` `assist_rate=0.0769` `provider_weight=0.1441`	-

Izan Merino M 73 0 0.09 0.00 2293% 0 0.1 6.8 40.8 13 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=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Matteo Prati', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.463, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0191, 'skill_edge': -0.003, 'height_edge': 0.016, 'attacker_skill': 0.4663, 'defender_skill': 0.473, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Matteo Prati', 'market_value': 5000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.473}], 'xg_override': 0.0355}	aerialWon: 0.0 -> 1.2 totalShots: 0.4362 -> 0.4445 shotOffTarget: 0.3087 -> 0.3146
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0355 -> 0.0869 expected_assists: 0.0319 -> 0.0587
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 70.0)	`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=0.0832` `goal_rate=0.0587` `scorer_weight=0.1086`	-
`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=0.057` `assist_rate=0.0492` `provider_weight=0.0711`	-

Ramón Enríquez M 75 0 0.07 - n/a 0 0.0 6.9 47.2 13 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 0.9932, quality 0.437)	`market_value_eur=380000` `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': 'Matteo Prati', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.398, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9235, 'skill_edge': -0.016, 'height_edge': -0.036, 'attacker_skill': 0.4374, 'defender_skill': 0.473, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Matteo Prati', 'market_value': 5000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.473}], 'xg_override': 0.0289}	aerialWon: 0.1577 -> 0.9 totalShots: 0.3387 -> 0.3128 shotOffTarget: 0.2309 -> 0.2132 onTargetScoringAttempt: 0.1078 -> 0.0996
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0289 -> 0.0707 expected_assists: 0.0418 -> 0.077
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 65.0)	`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=0.0683` `goal_rate=0.048` `scorer_weight=0.0878`	-
`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=0.0741` `assist_rate=0.0593` `provider_weight=0.0917`	-

David Larrubia F 81 0 0.21 0.05 352% 1 1.1 6.9 51.5 22 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9975, quality 0.478)	`market_value_eur=6300000` `quality_factor=0.4781` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=11` `history_shrink=0.3125`	-
`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': 'Alvaro Mantilla, Jeanuël Belocian', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9017, 'skill_edge': -0.0189, 'height_edge': -0.048, 'attacker_skill': 0.4781, 'defender_skill': 0.52, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Alvaro Mantilla', 'market_value': 1200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Jeanuël Belocian', 'market_value': 12900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6027}], 'xg_override': 0.0845}	totalShots: 1.1797 -> 1.0637 shotOffTarget: 0.7219 -> 0.6509 onTargetScoringAttempt: 0.4578 -> 0.4128 goals: 0.1081 -> 0.0975 expectedGoals: 0.0937 -> 0.0845
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.45 (squad xG sum 0.5938, xG scale 2.4468, xA scale 1.8415, team xA 1.16 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.453` `squad_xg_sum=0.5938` `squad_xa_sum=0.6312` `team_expected_assists=1.1624` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0845 -> 0.2068 expected_assists: 0.1729 -> 0.3185
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 81.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1868` `goal_rate=0.0975` `scorer_weight=0.2268`	-
`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=0.2728` `assist_rate=0.0` `provider_weight=0.2548`	-

Team totals 1 1.45 8 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Carlos Lopez	G	4.4m	10.9%	Market-value substitute prior
Adam Aznou	D	13.7m	30.6%	Market-value substitute prior
Jose Salinas	D	13.6m	29.9%	Market-value substitute prior
Jens-Lys Cajuste	M	22.1m	50.7%	Market-value substitute prior
Aarón Ochoa	M	22.0m	49.9%	Market-value substitute prior
Chupete	F	25.7m	57.6%	Market-value substitute prior

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

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

Julen Agirrezabala G 90 0 0.00 - n/a 0.0 6.8 39.2 19 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9989, quality 0.481)	`market_value_eur=6500000` `quality_factor=0.4805` `boost_factor=0.9989` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`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 Martínez, David Larrubia', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.0243}`	-
`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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	shots_faced: 9.7 -> 13.8 expected_saves: 2.37 -> 3.38 high_pressure_saves: 0.82 -> 1.16
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 82.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.2806`	-
`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=0.9553`	-

Alvaro Mantilla D 87 0 0.07 0.02 176% 0 0.2 6.8 41.4 14 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 0.9928, quality 0.437)	`market_value_eur=1200000` `quality_factor=0.4374` `boost_factor=0.9928` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'David Larrubia', '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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0394 -> 0.0652
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 77.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0631` `goal_rate=0.0` `scorer_weight=0.0522`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0236` `assist_rate=0.1938` `provider_weight=0.0299`	-

Jorge Salinas D 89 0 0.13 0.04 186% 1 0.6 6.8 50.7 13 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0000, quality 0.505)	`market_value_eur=8500000` `quality_factor=0.5047` `boost_factor=1.0` `reference_quality=0.505` `history_matches=10` `history_shrink=0.3333`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dani Lorenzo', 'matchup_zone': 'Right Mid vs Left Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0776 -> 0.1284 expected_assists: 0.2604 -> 0.2762
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 72.0)	`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=0.1205` `goal_rate=0.0` `scorer_weight=0.1027`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.2413` `assist_rate=0.1019` `provider_weight=0.221`	-

Pablo Ramón D 84 0 0.02 0.01 329% 1 0.2 6.9 39.0 14 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Pablo Martínez', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0137 -> 0.0227
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 69.0)	`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=0.0224` `goal_rate=0.0` `scorer_weight=0.0182`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0087` `assist_rate=0.0` `provider_weight=0.0075`	-

Jeanuël Belocian D 90 0 0.14 0.04 257% 1 0.5 6.7 35.5 11 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0069, quality 0.556)	`market_value_eur=12900000` `quality_factor=0.5559` `boost_factor=1.0069` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'David Larrubia', '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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0849 -> 0.1405
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 71.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1311` `goal_rate=0.2715` `scorer_weight=0.1756`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0088` `assist_rate=0.0` `provider_weight=0.0075`	-

Iván Martín M 86 0 0.07 0.03 166% 1 0.4 7.1 56.9 34 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 0.9979, quality 0.437)	`market_value_eur=2700000` `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': 'Einar Galilea', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.464, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9765, 'skill_edge': 0.0, 'height_edge': -0.016, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Einar Galilea', 'market_value': 365000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.0414}	aerialWon: 0.7754 -> 1.0 totalShots: 0.662 -> 0.6464 shotOffTarget: 0.4461 -> 0.4356 onTargetScoringAttempt: 0.2159 -> 0.2108
`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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0414 -> 0.0685
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0662` `goal_rate=0.0663` `scorer_weight=0.0856`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0646` `assist_rate=0.0788` `provider_weight=0.0761`	-

Matteo Prati M 81 0 0.06 0.01 894% 1 0.2 6.9 39.2 12 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 0.9946, quality 0.462)	`market_value_eur=5000000` `quality_factor=0.4622` `boost_factor=0.9946` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Izan Merino, Ramón Enríquez, Carlos Dotor', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel'}`	-
`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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0377 -> 0.0624
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 72.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0605` `goal_rate=0.0511` `scorer_weight=0.0719`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0418` `assist_rate=0.0566` `provider_weight=0.0504`	-

André Almeida M 69 0 0.09 0.02 513% 1 0.2 6.9 32.1 32 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 0.9982, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.9982` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`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': 'Rafa Garrido', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.516, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0533, 'skill_edge': 0.0122, 'height_edge': 0.024, 'attacker_skill': 0.4646, 'defender_skill': 0.4374, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Rafa Garrido', 'market_value': 1400000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.0572}	aerialWon: 0.0328 -> 0.9 totalShots: 0.732 -> 0.7711 shotOffTarget: 0.5002 -> 0.5269 onTargetScoringAttempt: 0.2318 -> 0.2442
`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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0572 -> 0.0947 expected_assists: 0.0967 -> 0.1026
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 74.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0904` `goal_rate=0.0703` `scorer_weight=0.1063`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0975` `assist_rate=0.0776` `provider_weight=0.0892`	-

Íñigo Sáinz-Maza M 83 0 0.06 - n/a 0 0.0 6.7 9.9 13 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 0.9855, quality 0.437)	`market_value_eur=1000000` `quality_factor=0.4374` `boost_factor=0.9855` `reference_quality=0.505` `history_matches=2` `history_shrink=0.7143`	-
`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': 'Ramón Enríquez', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0392 -> 0.0649
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 67.0)	`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=0.0628` `goal_rate=0.0459` `scorer_weight=0.0698`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0381` `assist_rate=0.0467` `provider_weight=0.0433`	-

Maguette Gueye M 87 0 0.14 0.03 306% 1 0.2 6.7 36.0 13 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 0.9916, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9916` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Carlos Dotor', 'matchup_zone': 'Attacking Mid vs Single Holding Mid — Space Creator Duel', 'duel_win_rate': 0.472, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0176, 'skill_edge': 0.0, 'height_edge': 0.012, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Carlos Dotor', 'market_value': 1200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0851}	aerialWon: 0.0826 -> 1.1 totalShots: 0.9464 -> 0.9631 shotOffTarget: 0.6832 -> 0.6952
`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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0851 -> 0.1408
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 69.0)	`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=0.1313` `goal_rate=0.0937` `scorer_weight=0.1498`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0351` `assist_rate=0.0496` `provider_weight=0.0425`	-

Iñigo Vicente F 86 0 0.13 0.03 318% 1 0.5 7.2 51.8 24 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 0.9977, quality 0.482)	`market_value_eur=6600000` `quality_factor=0.4818` `boost_factor=0.9977` `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': 'Ángel Recio, Fernando Calero', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.196, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.994, 'skill_edge': 0.0199, 'height_edge': -0.024, 'attacker_skill': 0.4818, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ángel Recio', 'market_value': 1000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Fernando Calero', 'market_value': 2100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.0787}	totalShots: 1.0533 -> 1.047
`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 1.20 (squad xG sum 0.7251, xG scale 1.6551, xA scale 1.0606, team xA 0.96 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.2` `squad_xg_sum=0.7251` `squad_xa_sum=0.9051` `team_expected_assists=0.96` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0787 -> 0.1303 expected_assists: 0.2773 -> 0.2941
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 77.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1222` `goal_rate=0.1093` `scorer_weight=0.1613`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.2548` `assist_rate=0.3159` `provider_weight=0.3288`	-

Team totals 0 1.20 11 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Simon Eriksson	G	4.4m	10.9%	Market-value substitute prior
Facundo González	D	13.6m	29.9%	Market-value substitute prior
Pedro Felipe	D	13.6m	29.9%	Market-value substitute prior
Aarón Martín	M	22.1m	50.3%	Market-value substitute prior
Andrés Vallecillo	M	22.0m	49.9%	Market-value substitute prior
Yassir Zabiri	F	26.1m	59.7%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Izan Merino vs André Almeida will be the pivotal duel. Total antagonist xG — Home: 0.38, Away: 0.26. Home danger zone: Left Mid vs Right Back — Wide Channel. Away danger zone: Attacking Mid vs Single Holding Mid — Space Creator Duel.

Midfield — possession 49.9% / 50.1%, dominance ratio 0.50, key duel: Izan Merino vs André Almeida

David Larrubia xG 0.08Pablo Martínez xG 0.10Dani Lorenzo xG 0.06Iván Martín xG 0.04Maguette Gueye xG 0.09André Almeida xG 0.06

Summary

Antagonist matchup analysis for Málaga vs Racing Club. Most likely scoreline: 1-0. Lambdas derived from 6 home and 4 away individual player duels. Head-to-head: Málaga 4W-3D-3L vs Racing Club over 10 meetings.

Tactical parity between 4-1-4-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Izan Merino vs André Almeida will be the pivotal duel. Total antagonist xG — Home: 0.38, Away: 0.26. Home danger zone: Left Mid vs Right Back — Wide Channel. Away danger zone: Attacking Mid vs Single Holding Mid — Space Creator Duel.

Leeds vs Tottenham

Premier League · 20261107 · 3-4-2-1 vs 4-2-3-1

Predicted 1-1Winner: DrawWinning H 1-0 (8.9%)Winning A 0-1 (8.1%)Confidence 0.65λ home/away 1.46 / 1.33Most-likely P 12.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Leeds vs Tottenham. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 3-4-2-1 vs 4-2-3-1 (duel lambdas: Home 1.289, Away 1.117). Final calibrated Poisson lambdas: Home 1.455, Away 1.326 (most likely score 1-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.29 / 1.12 Final λ (H/A) 1.46 / 1.33

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	Leeds	Tottenham
League position	11.00	8.00
Points per game	1.28	1.34
Attack index	0.93	0.88
Defense (concede) index	0.88	0.89
Form multiplier	1.00	1.00
Standing λ multiplier	0.92	0.91

Lambda decomposition (how the goal rates were built)

Stage	Leeds λ	Tottenham λ
Pre-competitive-floor	1.243	1.157
Pre-calibration (Micro-duels)	1.289	1.117
Final λ	1.455	1.326

competition calibration scale 1.159competition 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	12.1%
1-0	8.9%
2-1	8.7%
0-1	8.1%
1-2	7.9%

Home win	40.2%
Draw	25.6%
Away win	34.3%
Over 2.5	52.6%
BTTS yes	56.4%

Pregame fair line — favorite Leeds (40.2%), fair total 2.78, fair spread 0.13

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.

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

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

James Trafford G 90 0 0.00 - n/a 0.0 7.2 21.3 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 1.0221, quality 0.770)	`market_value_eur=38000000` `quality_factor=0.7699` `boost_factor=1.0221` `reference_quality=0.505` `history_matches=13` `history_shrink=0.2778`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0241)	`blend_weight=0.0241` `history_matches=13` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Richarlison, Xavi Simons', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.1168}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	shots_faced: 10.6 -> 12.6 expected_saves: 2.59 -> 3.08 high_pressure_saves: 0.89 -> 1.06
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 79.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=1.4716`	-
`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=0.8556`	-

James Justin D 88 0 0.07 0.06 ok 1 0.9 6.8 61.1 36 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 1.0031, quality 0.595)	`market_value_eur=16500000` `quality_factor=0.5953` `boost_factor=1.0031` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0101)	`blend_weight=0.0101` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9763` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.2335 -> 1.2457 totalCross: 2.45 -> 2.4401
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Mateus Fernandes', 'matchup_zone': 'LW vs CB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0593 -> 0.0733 expected_assists: 0.1343 -> 0.171
`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=0.0707` `goal_rate=0.1231` `scorer_weight=0.0916`	-
`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=0.1572` `assist_rate=0.0708` `provider_weight=0.1368`	-

Tarik Muharemović D 90 0 0.09 0.04 90% 1 0.5 7.1 45.8 14 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0311, quality 0.796)	`market_value_eur=43000000` `quality_factor=0.7957` `boost_factor=1.0311` `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`	interceptionWon: 1.1959 -> 1.2208 wasFouled: 0.9384 -> 0.9248 totalCross: 0.0645 -> 0.078 onTargetScoringAttempt: 0.2259 -> 0.2344 totalShots: 0.7409 -> 0.7334 goalAssist: 0.2348 -> 0.2275
`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': 'Richarlison', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0688 -> 0.085 expected_assists: 0.0302 -> 0.0385
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 75.0)	`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=0.0815` `goal_rate=0.0` `scorer_weight=0.068`	-
`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=0.0378` `assist_rate=0.2275` `provider_weight=0.0481`	-

Joe Rodon D 81 0 0.03 0.02 66% 0 0.3 6.8 50.2 24 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0041, quality 0.619)	`market_value_eur=18800000` `quality_factor=0.6191` `boost_factor=1.0041` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0072)	`blend_weight=0.0072` `history_matches=37` `season_overlap_discount=1.0` `per90_to_match_factor=0.9043` `prior_reliability=0.0933` `competition=Premier League`	fouls: 0.842 -> 0.8499
`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': 'Richarlison', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0282 -> 0.0348 expected_assists: 0.0249 -> 0.0317
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 77.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0342` `goal_rate=0.004` `scorer_weight=0.0278`	-
`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=0.0312` `assist_rate=0.0` `provider_weight=0.0254`	-

Ethan Ampadu M 90 0 0.05 0.05 ok 1 0.5 7.0 61.0 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 1.0072, quality 0.739)	`market_value_eur=33000000` `quality_factor=0.7389` `boost_factor=1.0072` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.998` `prior_reliability=0.1333` `competition=Premier League`	fouls: 2.3232 -> 2.3159
`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': 'Archie Gray', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.422, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9583, 'skill_edge': -0.0084, 'height_edge': -0.02, 'attacker_skill': 0.7622, 'defender_skill': 0.7808, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Archie Gray', 'market_value': 34000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7808}], 'xg_override': 0.0411}	totalShots: 0.5886 -> 0.5641 aerialWon: 1.1228 -> 1.1 shotOffTarget: 0.4337 -> 0.4156 onTargetScoringAttempt: 0.1542 -> 0.1478
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0411 -> 0.0508 expected_assists: 0.0655 -> 0.0834
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 80.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0495` `goal_rate=0.0465` `scorer_weight=0.0538`	-
`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=0.08` `assist_rate=0.0667` `provider_weight=0.0843`	-

Gabriel Gudmundsson M 83 0 0.04 0.01 360% 1 0.3 6.8 41.9 34 FBref Prior 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 1.0062, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0062` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`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': 'Archie Gray', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.394, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9173, 'skill_edge': -0.0322, 'height_edge': -0.024, 'attacker_skill': 0.7091, 'defender_skill': 0.7808, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Archie Gray', 'market_value': 34000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7808}], 'xg_override': 0.0354}	aerialWon: 0.4332 -> 1.1 totalShots: 0.6321 -> 0.5798 shotOffTarget: 0.4324 -> 0.3966 onTargetScoringAttempt: 0.1997 -> 0.1832
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0354 -> 0.0437 expected_assists: 0.0719 -> 0.0915
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 78.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0428` `goal_rate=0.0436` `scorer_weight=0.0479`	-
`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=0.0874` `assist_rate=0.0828` `provider_weight=0.0997`	-

Jayden Bogle M 83 0 0.16 0.08 100% 1 0.6 6.9 57.1 30 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0037, quality 0.623)	`market_value_eur=19200000` `quality_factor=0.6231` `boost_factor=1.0037` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0077)	`blend_weight=0.0077` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9211` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 1.2203 -> 1.2317 totalCross: 3.1046 -> 3.0933 totalShots: 1.0977 -> 1.0893
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Andy Robertson', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run', 'duel_win_rate': 0.475, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1103, 'skill_edge': 0.0751, 'height_edge': 0.0, 'attacker_skill': 0.6976, 'defender_skill': 0.5308, 'attacker_role': 'LWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Andy Robertson', 'market_value': 7500000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.5308}], 'xg_override': 0.1271}	aerialWon: 1.1604 -> 1.0 totalShots: 1.0949 -> 1.2157 shotOffTarget: 0.7369 -> 0.8182 onTargetScoringAttempt: 0.358 -> 0.3975 expectedGoalsOnTarget: 0.1435 -> 0.1593 expectedGoals: 0.1145 -> 0.1271 bigChanceMissed: 0.1082 -> 0.1201 goals: 0.0915 -> 0.1016
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1271 -> 0.1571 expected_assists: 0.1114 -> 0.1418
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 76.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1454` `goal_rate=0.1016` `scorer_weight=0.1345`	-
`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=0.1322` `assist_rate=0.0921` `provider_weight=0.1248`	-

Ao Tanaka M 76 0 0.09 0.05 71% 1 0.4 6.9 38.1 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 1.0032, quality 0.592)	`market_value_eur=16200000` `quality_factor=0.5921` `boost_factor=1.0032` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0026)	`blend_weight=0.0026` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.845` `prior_reliability=0.0333` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Marcos Senesi', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run', 'duel_win_rate': 0.373, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9599, 'skill_edge': -0.0113, 'height_edge': -0.016, 'attacker_skill': 0.6608, 'defender_skill': 0.6858, 'attacker_role': 'RWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Marcos Senesi', 'market_value': 18200000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.6858}], 'xg_override': 0.0691}	aerialWon: 0.1947 -> 1.1 totalShots: 0.9906 -> 0.9509 shotOffTarget: 0.7222 -> 0.6932 onTargetScoringAttempt: 0.2684 -> 0.2576
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0691 -> 0.0854 expected_assists: 0.0533 -> 0.0679
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0819` `goal_rate=0.0706` `scorer_weight=0.0865`	-
`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=0.0656` `assist_rate=0.055` `provider_weight=0.069`	-

Dominic Calvert-Lewin F 86 1 0.42 0.40 ok 2 1.7 6.8 56.7 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 1.0058, quality 0.694)	`market_value_eur=27000000` `quality_factor=0.6941` `boost_factor=1.0058` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9602` `prior_reliability=0.1333` `competition=Premier League`	totalOffside: 0.645 -> 0.652 wasFouled: 1.2147 -> 1.2082
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Jan Paul van Hecke, Micky van de Ven', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8567, 'skill_edge': -0.0815, 'height_edge': -0.016, 'attacker_skill': 0.6941, 'defender_skill': 0.8752, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Jan Paul van Hecke', 'market_value': 65000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.887}, {'player': 'Micky van de Ven', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}], 'xg_override': 0.3409}	totalShots: 2.1413 -> 1.8345 shotOffTarget: 1.2045 -> 1.0319 onTargetScoringAttempt: 0.9346 -> 0.8007 bigChanceMissed: 0.6078 -> 0.5207 expectedGoalsOnTarget: 0.4689 -> 0.4017 expectedGoals: 0.3979 -> 0.3409 goals: 0.3654 -> 0.313
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3409 -> 0.4212 expected_assists: 0.0317 -> 0.0404
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 79.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3437` `goal_rate=0.313` `scorer_weight=0.3911`	-
`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=0.0396` `assist_rate=0.0026` `provider_weight=0.0323`	-

Noah Okafor F 72 0 0.21 0.11 91% 2 0.9 6.8 54.2 27 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0090, quality 0.752)	`market_value_eur=35000000` `quality_factor=0.752` `boost_factor=1.009` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0053)	`blend_weight=0.0053` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.7998` `prior_reliability=0.0667` `competition=Premier League`	totalCross: 1.9211 -> 1.9321 wonTackle: 0.697 -> 0.706
`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': 'Archie Gray, Jan Paul van Hecke', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.221, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9281, 'skill_edge': -0.0369, 'height_edge': -0.012, 'attacker_skill': 0.752, 'defender_skill': 0.8339, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Archie Gray', 'market_value': 34000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7808}, {'player': 'Jan Paul van Hecke', 'market_value': 65000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.887}], 'xg_override': 0.1697}	totalShots: 1.767 -> 1.64 shotOffTarget: 1.1473 -> 1.0648 onTargetScoringAttempt: 0.6174 -> 0.573 goals: 0.2282 -> 0.2118 expectedGoalsOnTarget: 0.1974 -> 0.1832 expectedGoals: 0.1829 -> 0.1697 bigChanceMissed: 0.1055 -> 0.0979
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1697 -> 0.2097 expected_assists: 0.073 -> 0.0929
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 77.0)	`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=0.1892` `goal_rate=0.2118` `scorer_weight=0.2499`	-
`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=0.0887` `assist_rate=0.0418` `provider_weight=0.0743`	-

Mateo Joseph F 78 0 0.15 0.08 84% 1 0.6 6.7 48.1 18 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 0.9974, quality 0.446)	`market_value_eur=3700000` `quality_factor=0.4461` `boost_factor=0.9974` `reference_quality=0.505` `history_matches=29` `history_shrink=0.1471`	-
`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': 'Archie Gray, Jan Paul van Hecke', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.6964, 'skill_edge': -0.1745, 'height_edge': -0.032, 'attacker_skill': 0.4461, 'defender_skill': 0.8339, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Archie Gray', 'market_value': 34000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7808}, {'player': 'Jan Paul van Hecke', 'market_value': 65000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.887}], 'xg_override': 0.1178}	totalShots: 1.3902 -> 0.9681 shotOffTarget: 0.8378 -> 0.5834 onTargetScoringAttempt: 0.5524 -> 0.3847 bigChanceMissed: 0.3987 -> 0.2777 expectedGoalsOnTarget: 0.2715 -> 0.1891 goals: 0.2073 -> 0.1444 expectedGoals: 0.1691 -> 0.1178
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.46 (squad xG sum 1.1774, xG scale 1.2358, xA scale 1.2732, team xA 0.95 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.455` `squad_xg_sum=1.1774` `squad_xa_sum=0.7428` `team_expected_assists=0.9458` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1178 -> 0.1456 expected_assists: 0.0614 -> 0.0782
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 72.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1355` `goal_rate=0.1444` `scorer_weight=0.1687`	-
`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=0.0752` `assist_rate=0.0` `provider_weight=0.0626`	-

Team totals 1 1.46 13 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Michael Zetterer	G	4.5m	11.1%	Market-value substitute prior
Jaka Bijol	D	14.3m	23.1%	Market-value substitute prior
Nico Elvedi	D	37.6m	61.0%	Market-value substitute prior
Anton Stach	M	23.1m	33.0%	Market-value substitute prior
Sean Longstaff	M	15.0m	70.0%	Market-value substitute prior
Jean-Mattéo Bahoya	F	26.2m	60.0%	Market-value substitute prior

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

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

Antonín Kinský G 90 0 0.00 - n/a 0.0 6.9 32.7 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 1.0082, quality 0.620)	`market_value_eur=18900000` `quality_factor=0.6201` `boost_factor=1.0082` `reference_quality=0.505` `history_matches=16` `history_shrink=0.2381`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0206)	`blend_weight=0.0206` `history_matches=16` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.847 -> 2.8398
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dominic Calvert-Lewin, Noah Okafor', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.289}`	-
`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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	shots_faced: 12.2 -> 13.8 expected_saves: 2.98 -> 3.38 high_pressure_saves: 1.03 -> 1.16
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 77.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.4241`	-
`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=1.0537`	-

Jan Paul van Hecke D 90 0 0.26 0.10 167% 1 0.7 7.6 62.0 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0107, quality 0.863)	`market_value_eur=65000000` `quality_factor=0.8627` `boost_factor=1.0107` `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=0.9984` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.168 -> 1.1622 totalShots: 1.1075 -> 1.1022
`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': 'Dominic Calvert-Lewin', '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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2257 -> 0.2625
`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=0.2309` `goal_rate=0.2653` `scorer_weight=0.3002`	-
`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=0.0814` `assist_rate=0.0196` `provider_weight=0.0679`	-

Marcos Senesi D 90 0 0.03 0.03 ok 0 0.3 7.2 46.4 33 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0037, quality 0.613)	`market_value_eur=18200000` `quality_factor=0.613` `boost_factor=1.0037` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0049)	`blend_weight=0.0049` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9976` `prior_reliability=0.0667` `competition=Premier League`	wonTackle: 1.0813 -> 1.0956 wasFouled: 1.3453 -> 1.3534
`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': 'Ao Tanaka', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run'}`	-
`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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 82.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0249` `goal_rate=0.0` `scorer_weight=0.0202`	-
`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=0.0627` `assist_rate=0.0664` `provider_weight=0.0672`	-

Andy Robertson D 79 0 0.07 0.04 99% 1 0.4 6.6 43.4 33 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9995, quality 0.493)	`market_value_eur=7500000` `quality_factor=0.4927` `boost_factor=0.9995` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0100)	`blend_weight=0.01` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.8784` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 0.1507 -> 0.1595 totalCross: 4.8941 -> 4.8865
`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': 'Jayden Bogle', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run'}`	-
`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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.061 -> 0.071 expected_assists: 0.1976 -> 0.2058
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 18 by projected rating, fifa_overall 85.0)	`match_squad_rank=18` `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=0.0685` `goal_rate=0.0403` `scorer_weight=0.0578`	-
`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=0.186` `assist_rate=0.2097` `provider_weight=0.2159`	-

Micky van de Ven D 89 0 0.07 0.05 35% 1 0.3 7.1 57.2 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 1.0099, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0099` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0045)	`blend_weight=0.0045` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9853` `prior_reliability=0.0667` `competition=Premier League`	fouls: 0.7554 -> 0.7609
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dominic Calvert-Lewin', '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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0563 -> 0.0655
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 81.0)	`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=0.0634` `goal_rate=0.009` `scorer_weight=0.0524`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0234` `assist_rate=0.0036` `provider_weight=0.019`	-

Sandro Tonali M 87 0 0.07 0.06 ok 1 1.2 7.3 58.4 30 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0116, quality 0.884)	`market_value_eur=83000000` `quality_factor=0.8845` `boost_factor=1.0116` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0080)	`blend_weight=0.008` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9636` `prior_reliability=0.12` `competition=Premier League`	wonTackle: 1.4391 -> 1.4319 wasFouled: 0.8447 -> 0.8508 totalCross: 1.7062 -> 1.7011
`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 Ampadu', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.472, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.077, 'skill_edge': 0.0564, 'height_edge': -0.004, 'attacker_skill': 0.8875, 'defender_skill': 0.7622, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Ethan Ampadu', 'market_value': 33000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.7622}], 'xg_override': 0.0599}	aerialWon: 0.5449 -> 1.1 totalShots: 1.2346 -> 1.3297 shotOffTarget: 0.9456 -> 1.0184 onTargetScoringAttempt: 0.288 -> 0.3102 goals: 0.0889 -> 0.0957
`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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0599 -> 0.0697 expected_assists: 0.1308 -> 0.1362
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 85.0)	`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=0.0673` `goal_rate=0.0957` `scorer_weight=0.0871`	-
`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=0.1273` `assist_rate=0.1445` `provider_weight=0.1465`	-

Archie Gray M 79 0 0.06 0.04 48% 1 0.4 6.9 49.0 38 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 1.0098, quality 0.746)	`market_value_eur=34000000` `quality_factor=0.7455` `boost_factor=1.0098` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0100)	`blend_weight=0.01` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.8752` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 0.9615 -> 0.9724 totalShots: 0.6249 -> 0.6187
`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': 'Noah Okafor, Mateo Joseph, Ethan Ampadu', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0547 -> 0.0636
`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=0.0616` `goal_rate=0.0581` `scorer_weight=0.0657`	-
`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=0.0646` `assist_rate=0.0722` `provider_weight=0.0715`	-

Rodrigo Bentancur M 81 0 0.05 0.01 226% 1 0.2 6.9 49.5 20 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 1.0036, quality 0.594)	`market_value_eur=16399999` `quality_factor=0.5942` `boost_factor=1.0036` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.9049` `prior_reliability=0.1` `competition=Premier League`	fouls: 1.0556 -> 1.0781 wonTackle: 1.7571 -> 1.7629
`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': 'Jayden Bogle', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0391 -> 0.0455
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 79.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0445` `goal_rate=0.0467` `scorer_weight=0.0494`	-
`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=0.0274` `assist_rate=0.0492` `provider_weight=0.0347`	-

Mateus Fernandes M 83 0 0.10 0.04 138% 1 0.8 7.1 60.4 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 1.0109, quality 0.868)	`market_value_eur=68000000` `quality_factor=0.8677` `boost_factor=1.0109` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0065)	`blend_weight=0.0065` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9168` `prior_reliability=0.1` `competition=Premier League`	totalCross: 2.9692 -> 2.9777 wasFouled: 0.8038 -> 0.7986
`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 Justin', 'matchup_zone': 'LW vs CB', 'duel_win_rate': 0.498, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1144, 'skill_edge': 0.0978, 'height_edge': -0.02, 'attacker_skill': 0.8677, 'defender_skill': 0.6503, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'James Justin', 'market_value': 16500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6503}], 'xg_override': 0.0874}`	totalShots: 1.3287 -> 1.4807 shotOffTarget: 0.9826 -> 1.095 aerialWon: 0.9478 -> 1.0 onTargetScoringAttempt: 0.3461 -> 0.3857 goals: 0.111 -> 0.1237 expectedGoals: 0.0784 -> 0.0874 bigChanceMissed: 0.0487 -> 0.0543
`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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0874 -> 0.1017 expected_assists: 0.1233 -> 0.1284
`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=0.0967` `goal_rate=0.1237` `scorer_weight=0.1271`	-
`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=0.1205` `assist_rate=0.086` `provider_weight=0.1027`	-

Xavi Simons M 80 0 0.21 0.12 78% 2 1.5 6.9 51.5 19 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0132, quality 0.796)	`market_value_eur=43000000` `quality_factor=0.7957` `boost_factor=1.0132` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`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 Justin', 'matchup_zone': 'RW vs CB', 'duel_win_rate': 0.469, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0727, 'skill_edge': 0.0654, 'height_edge': -0.016, 'attacker_skill': 0.7957, 'defender_skill': 0.6503, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'James Justin', 'market_value': 16500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6503}], 'xg_override': 0.1833}`	aerialWon: 0.1706 -> 1.0 totalShots: 1.8823 -> 2.0192 shotOffTarget: 1.2265 -> 1.3157 onTargetScoringAttempt: 0.6558 -> 0.7035 bigChanceMissed: 0.3218 -> 0.3452 expectedGoalsOnTarget: 0.1911 -> 0.205 goals: 0.1839 -> 0.1973 expectedGoals: 0.1709 -> 0.1833
`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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1833 -> 0.2132 expected_assists: 0.158 -> 0.1645
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 81.0)	`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=0.192` `goal_rate=0.1973` `scorer_weight=0.226`	-
`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=0.1517` `assist_rate=0.1828` `provider_weight=0.1841`	-

Richarlison F 80 1 0.34 0.20 67% 2 1.5 6.7 48.0 21 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0028, quality 0.575)	`market_value_eur=14600000` `quality_factor=0.5748` `boost_factor=1.0028` `reference_quality=0.505` `history_matches=33` `history_shrink=0.1316`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0040)	`blend_weight=0.004` `history_matches=33` `season_overlap_discount=1.0` `per90_to_match_factor=0.89` `prior_reliability=0.0467` `competition=Premier League`	totalShots: 2.1606 -> 2.152 fouls: 0.9924 -> 0.9986
`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 Justin, Tarik Muharemović', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.8618, 'skill_edge': -0.078, 'height_edge': -0.016, 'attacker_skill': 0.5748, 'defender_skill': 0.7482, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'James Justin', 'market_value': 16500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6503}, {'player': 'Tarik Muharemović', 'market_value': 43000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8462}], 'xg_override': 0.2887}	totalShots: 2.1573 -> 1.8592 shotOffTarget: 1.3232 -> 1.1403 onTargetScoringAttempt: 0.8341 -> 0.7188 bigChanceMissed: 0.5291 -> 0.456 expectedGoalsOnTarget: 0.3983 -> 0.3433 goals: 0.3489 -> 0.3007 expectedGoals: 0.335 -> 0.2887
`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 1.33 (squad xG sum 1.1399, xG scale 1.1632, xA scale 1.0414, team xA 1.06 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=1.1399` `squad_xa_sum=1.0186` `team_expected_assists=1.0608` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2887 -> 0.3358
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 78.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.2852` `goal_rate=0.3007` `scorer_weight=0.3477`	-
`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=0.0369` `assist_rate=0.0375` `provider_weight=0.0382`	-

Team totals 1 1.33 12 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Brandon Austin	G	4.4m	10.9%	Market-value substitute prior
Pedro Porro	D	15.0m	24.6%	Market-value substitute prior
Destiny Udogie	D	14.2m	62.1%	Market-value substitute prior
Lucas Bergvall	M	23.4m	33.5%	Market-value substitute prior
Conor Gallagher	M	23.1m	33.0%	Market-value substitute prior
Omar Marmoush	F	26.9m	36.7%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Ethan Ampadu vs Sandro Tonali will be the pivotal duel. Total antagonist xG — Home: 0.90, Away: 0.62. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 48.7% / 51.3%, dominance ratio 0.45, key duel: Ethan Ampadu vs Sandro Tonali

Dominic Calvert-Lewin xG 0.34Noah Okafor xG 0.17Mateo Joseph xG 0.12Mateus Fernandes xG 0.09Sandro Tonali xG 0.06Xavi Simons xG 0.18

Summary

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

Tactical parity between 3-4-2-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Ethan Ampadu vs Sandro Tonali will be the pivotal duel. Total antagonist xG — Home: 0.90, Away: 0.62. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

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