Soccer predictions: actual data vs predicted data

Slate 20261101 · 5 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
Liverpool vs Arsenal Premier League	2-1	Liverpool	43.2% / 24.9% / 31.9%	54.4%	57.5%	0.72	1.55 / 1.30	-	pending
Racing Club vs Real Madrid LaLiga	0-2	Real Madrid	9.8% / 14.3% / 75.8%	71.4%	56.6%	0.81	0.92 / 2.77	-	pending
Athletic Club vs Real Sociedad LaLiga	2-1	Athletic Club	48.5% / 23.8% / 27.8%	57.3%	58.9%	0.74	1.73 / 1.25	-	pending
Getafe vs Sevilla LaLiga	1-2	Sevilla	30.6% / 24.2% / 45.2%	57.3%	59.5%	0.72	1.33 / 1.66	-	pending
Elche vs Valencia LaLiga	1-0	Elche	45.7% / 25.4% / 28.9%	51.1%	54.5%	0.72	1.54 / 1.18	-	pending

Match detail

Liverpool vs Arsenal

Premier League · 20261101 · 4-2-3-1 vs 4-2-3-1

Predicted 2-1Winner: LiverpoolWinning H 2-1 (9.0%)Winning A 1-2 (7.6%)Confidence 0.72λ home/away 1.55 / 1.30Most-likely P 9.0%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Liverpool vs Arsenal. 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 1.831, Away 1.525). Final calibrated Poisson lambdas: Home 1.554, Away 1.301 (most likely score 2-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (11 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.83 / 1.52 Final λ (H/A) 1.55 / 1.30

FBref Team Priors: Liverpool FC (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 2.759) vs Arsenal (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 2.759) | 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	Liverpool	Arsenal
League position	5.00	2.00
Points per game	1.65	2.08
Attack index	1.00	1.07
Defense (concede) index	0.78	0.89
Form multiplier	0.98	1.02
Standing λ multiplier	0.90	0.99

Lambda decomposition (how the goal rates were built)

Stage	Liverpool λ	Arsenal λ
FBref Squad Prior E[λ] (weight 0.192)	2.759	2.759
Pre-competitive-floor	1.844	1.514
Pre-calibration (Micro-duels)	1.831	1.525
Final λ	1.554	1.301

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

Scoreline distribution & markets

Top 5 scorelines	P
1-1	11.7%
2-1	9.0%
1-0	8.9%
1-2	7.6%
0-1	7.4%

Home win	43.2%
Draw	24.9%
Away win	31.9%
Over 2.5	54.4%
BTTS yes	57.5%

Pregame fair line — favorite Liverpool (43.2%), fair total 2.85, 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.

Liverpool — 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

Ronald Araújo D 76 0 0.02 0.03 32% 0 0.2 6.8 42.3 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 1.0077, quality 0.694)	`market_value_eur=27000000` `quality_factor=0.6941` `boost_factor=1.0077` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0023)	`blend_weight=0.0023` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.8461` `prior_reliability=0.0267` `competition=Premier League`	fouls: 0.585 -> 0.5935
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kai Havertz', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 80.0)	`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=0.0223` `goal_rate=0.0587` `scorer_weight=0.0282`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0248` `assist_rate=0.0` `provider_weight=0.0201`	-

Jérémy Jacquet D 88 0 0.04 0.02 106% 1 0.1 7.0 43.3 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 1.0417, quality 0.866)	`market_value_eur=67000000` `quality_factor=0.8661` `boost_factor=1.0417` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0267)	`blend_weight=0.0267` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.9767` `prior_reliability=0.1067` `competition=Premier League`	interceptionWon: 1.2618 -> 1.2933 wasFouled: 0.8034 -> 0.8308 totalShots: 0.5176 -> 0.5038 fouls: 1.056 -> 1.0441
`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': 'Kai Havertz', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 77.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0433` `goal_rate=0.0` `scorer_weight=0.0354`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0267` `assist_rate=0.0` `provider_weight=0.0217`	-

Virgil van Dijk D 90 0 0.06 0.10 39% 1 0.7 7.1 59.5 34 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0023, quality 0.585)	`market_value_eur=15500000` `quality_factor=0.5846` `boost_factor=1.0023` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0085)	`blend_weight=0.0085` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.1607 -> 1.1551
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kai Havertz', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	-
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0578` `goal_rate=0.1139` `scorer_weight=0.0744`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.027` `assist_rate=0.0` `provider_weight=0.0219`	-

Miloš Kerkez D 86 0 0.02 0.02 34% 0 0.2 6.7 48.5 34 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0081, quality 0.758)	`market_value_eur=36000000` `quality_factor=0.7581` `boost_factor=1.0081` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0083)	`blend_weight=0.0083` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.958` `prior_reliability=0.12` `competition=Premier League`	totalShots: 0.3729 -> 0.3788 wasFouled: 1.7578 -> 1.752
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Martin Ødegaard', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `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 81.0)	`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=0.0246` `goal_rate=0.0378` `scorer_weight=0.0285`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0212` `assist_rate=0.0155` `provider_weight=0.0206`	-

Ryan Gravenberch M 79 0 0.06 0.03 90% 1 0.8 6.9 56.2 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 1.0118, quality 0.883)	`market_value_eur=81000000` `quality_factor=0.8829` `boost_factor=1.0118` `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=0.8771` `prior_reliability=0.0733` `competition=Premier League`	wasFouled: 1.1199 -> 1.1302
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.425, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.007, 'skill_edge': -0.0033, 'height_edge': 0.008, 'attacker_skill': 0.8915, 'defender_skill': 0.8988, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Declan Rice', 'market_value': 114000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8988}], 'xg_override': 0.0686}	aerialWon: 1.0941 -> 1.3 totalShots: 1.0181 -> 1.0252 shotOffTarget: 0.7305 -> 0.7356
`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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0445 -> 0.0532
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 85.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.062` `goal_rate=0.0743` `scorer_weight=0.0671`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0518` `assist_rate=0.0793` `provider_weight=0.0665`	-

Alexis Mac Allister M 88 0 0.12 0.08 42% 1 1.2 7.1 56.4 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 1.0112, quality 0.879)	`market_value_eur=77000000` `quality_factor=0.8792` `boost_factor=1.0112` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0052)	`blend_weight=0.0052` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9791` `prior_reliability=0.08` `competition=Premier League`	wasFouled: 0.7451 -> 0.754 totalShots: 1.6246 -> 1.6162 totalCross: 1.1751 -> 1.169 fouls: 1.2924 -> 1.2984
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.368, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9232, 'skill_edge': -0.0043, 'height_edge': -0.048, 'attacker_skill': 0.8893, 'defender_skill': 0.8988, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Declan Rice', 'market_value': 114000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8988}], 'xg_override': 0.1268}	totalShots: 1.6218 -> 1.4973 shotOffTarget: 1.0864 -> 1.003 onTargetScoringAttempt: 0.5354 -> 0.4943 goals: 0.1411 -> 0.1303 expectedGoals: 0.1373 -> 0.1268 expectedGoalsOnTarget: 0.0719 -> 0.0664
`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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1268 -> 0.1183 expected_assists: 0.1153 -> 0.1379
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 84.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1116` `goal_rate=0.1303` `scorer_weight=0.1206`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1288` `assist_rate=0.0871` `provider_weight=0.1144`	-

Bradley Barcola F 80 0 0.16 0.08 94% 2 0.7 6.9 41.1 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 1.0528, quality 0.892)	`market_value_eur=97000000` `quality_factor=0.8922` `boost_factor=1.0528` `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': 'Ben White, Gabriel Magalhães', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.198, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9977, 'skill_edge': 0.0224, 'height_edge': -0.024, 'attacker_skill': 0.8922, 'defender_skill': 0.8424, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ben White', 'market_value': 32000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7941}, {'player': 'Gabriel Magalhães', 'market_value': 70000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8907}], 'xg_override': 0.1704}	-
`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`	assists: 1.0 -> 0
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1704 -> 0.159 expected_assists: 0.124 -> 0.1483
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 85.0)	`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=0.147` `goal_rate=0.1784` `scorer_weight=0.1648`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1378` `assist_rate=0.5251` `provider_weight=0.1854`	-

Florian Wirtz M 79 0 0.15 0.17 ok 2 1.5 7.0 54.8 30 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0123, quality 0.883)	`market_value_eur=81000000` `quality_factor=0.8829` `boost_factor=1.0123` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0080)	`blend_weight=0.008` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.8807` `prior_reliability=0.1133` `competition=Premier League`	fouls: 1.6631 -> 1.6539 totalCross: 1.9423 -> 1.935 totalShots: 1.7368 -> 1.7438
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Myles Lewis-Skelly', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.464, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9758, 'skill_edge': -0.0045, 'height_edge': -0.012, 'attacker_skill': 0.8829, 'defender_skill': 0.8928, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Myles Lewis-Skelly', 'market_value': 69000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8928}], 'xg_override': 0.1615}	aerialWon: 0.3131 -> 0.9 totalShots: 1.7438 -> 1.7016 shotOffTarget: 1.1296 -> 1.1023 onTargetScoringAttempt: 0.6106 -> 0.5958
`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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1615 -> 0.1507 expected_assists: 0.1688 -> 0.2019
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 86.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1399` `goal_rate=0.1582` `scorer_weight=0.1483`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1828` `assist_rate=0.1523` `provider_weight=0.1867`	-

Cody Gakpo F 85 1 0.27 0.16 71% 3 1.9 6.9 50.3 43 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 1.0118, quality 0.873)	`market_value_eur=72000000` `quality_factor=0.8734` `boost_factor=1.0118` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0083)	`blend_weight=0.0083` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9451` `prior_reliability=0.12` `competition=Premier League`	totalCross: 1.2197 -> 1.2444 interceptionWon: 0.8915 -> 0.9015 totalShots: 2.257 -> 2.2648 fouls: 1.3775 -> 1.3835 wonTackle: 0.8734 -> 0.8792
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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, Gabriel Magalhães', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.234, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 1.0499, 'skill_edge': 0.014, 'height_edge': 0.02, 'attacker_skill': 0.8734, 'defender_skill': 0.8424, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ben White', 'market_value': 32000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7941}, {'player': 'Gabriel Magalhães', 'market_value': 70000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8907}], 'xg_override': 0.2858}	totalShots: 2.2648 -> 2.3778 shotOffTarget: 1.5313 -> 1.6077 onTargetScoringAttempt: 0.7241 -> 0.7602 expectedGoals: 0.2722 -> 0.2858 goals: 0.2467 -> 0.259 bigChanceMissed: 0.2068 -> 0.2171 expectedGoalsOnTarget: 0.1266 -> 0.1329
`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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2858 -> 0.2667 expected_assists: 0.1169 -> 0.1398
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 82.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2341` `goal_rate=0.259` `scorer_weight=0.2454`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1305` `assist_rate=0.3732` `provider_weight=0.1748`	-

Alisson G 90 0 0.00 - n/a 0.0 7.0 53.0 27 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0035, quality 0.595)	`market_value_eur=16500000` `quality_factor=0.5953` `boost_factor=1.0035` `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=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.8471 -> 2.8377
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Kai Havertz, Martin Ødegaard', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.5252}`	-
`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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	shots_faced: 14.5 -> 12.4 expected_saves: 3.55 -> 3.04 high_pressure_saves: 1.22 -> 1.04
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 87.0)	`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=0.0` `scorer_weight=0.0` `squad_weight_total=1.6565`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.9945`	-

Alexander Isak F 79 1 0.44 0.27 66% 3 1.2 6.9 43.4 18 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 1.0222, quality 0.891)	`market_value_eur=93000000` `quality_factor=0.8905` `boost_factor=1.0222` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0167)	`blend_weight=0.0167` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.8823` `prior_reliability=0.1333` `competition=Premier League`	wasFouled: 0.2838 -> 0.2938 totalShots: 2.7489 -> 2.7546
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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, Gabriel Magalhães', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.242, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 1.0612, 'skill_edge': 0.0217, 'height_edge': 0.02, 'attacker_skill': 0.8905, 'defender_skill': 0.8424, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ben White', 'market_value': 32000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7941}, {'player': 'Gabriel Magalhães', 'market_value': 70000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8907}], 'xg_override': 0.4763}	totalShots: 2.7546 -> 2.9232 shotOffTarget: 1.622 -> 1.7213 onTargetScoringAttempt: 1.1302 -> 1.1994 expectedGoalsOnTarget: 0.6991 -> 0.7419 goals: 0.5384 -> 0.5714 expectedGoals: 0.4488 -> 0.4763 bigChanceMissed: 0.3738 -> 0.3967
`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 1.55 (squad xG sum 1.6653, xG scale 0.9332, xA scale 1.1959, team xA 1.01 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.554` `squad_xg_sum=1.6653` `squad_xa_sum=0.8446` `team_expected_assists=1.0101` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.4763 -> 0.4446 expected_assists: 0.0388 -> 0.0464
`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` `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=0.3589` `goal_rate=0.5714` `scorer_weight=0.5249`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0453` `assist_rate=0.02` `provider_weight=0.0371`	-

Team totals 2 1.55 17 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Giorgi Mamardashvili	G	5.5m	15.8%	Market-value substitute prior
Jeremie Frimpong	D	14.8m	35.6%	Market-value substitute prior
Curtis Jones	D	14.8m	35.3%	Market-value substitute prior
Dominik Szoboszlai	M	23.8m	58.0%	Market-value substitute prior
Mohamed Salah	M	22.8m	53.5%	Market-value substitute prior
Hugo Ekitiké	F	27.0m	63.8%	Market-value substitute prior

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': 'Alexander Isak, Cody Gakpo', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.8305}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	shots_faced: 17.4 -> 14.8 expected_saves: 4.26 -> 3.63 high_pressure_saves: 1.46 -> 1.24
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 88.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3395`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=1.0624`	-

Ben White D 75 0 0.02 0.01 99% 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': 'Alexander Isak', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.1179 -> 0.1073
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 86.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0191` `goal_rate=0.0` `scorer_weight=0.0154`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1017` `assist_rate=0.363` `provider_weight=0.1341`	-

Ezri Konsa D 90 0 0.09 0.05 77% 1 0.4 6.9 52.4 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0107, quality 0.834)	`market_value_eur=53000000` `quality_factor=0.834` `boost_factor=1.0107` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0005)	`blend_weight=0.0005` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.9999` `prior_reliability=0.0067` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Cody Gakpo', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0948 -> 0.0887
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0849` `goal_rate=0.1542` `scorer_weight=0.1109`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0076` `assist_rate=0.0` `provider_weight=0.0065`	-

Gabriel Magalhães D 90 0 0.19 0.10 101% 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': 'Alexander Isak', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2057 -> 0.1924
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 88.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.175` `goal_rate=0.1574` `scorer_weight=0.1561`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0327` `assist_rate=0.0221` `provider_weight=0.0277`	-

Myles Lewis-Skelly D 74 0 0.02 0.01 78% 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': 'Florian Wirtz', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0944 -> 0.0859
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 78.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0197` `goal_rate=0.0` `scorer_weight=0.0159`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0823` `assist_rate=0.0` `provider_weight=0.0687`	-

Declan Rice M 86 0 0.06 0.04 41% 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': 'Ryan Gravenberch', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.415, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.993, 'skill_edge': 0.0033, 'height_edge': -0.008, 'attacker_skill': 0.8988, 'defender_skill': 0.8915, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Ryan Gravenberch', 'market_value': 81000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8915}], 'xg_override': 0.0627}	aerialWon: 0.988 -> 1.2 totalShots: 0.9942 -> 0.9872 shotOffTarget: 0.7469 -> 0.7417
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.2143 -> 0.1951
`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=0.0569` `goal_rate=0.0847` `scorer_weight=0.07`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1772` `assist_rate=0.2552` `provider_weight=0.2253`	-

Bruno Guimarães M 79 0 0.07 0.12 42% 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': 'Ryan Gravenberch', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.387, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9515, 'skill_edge': -0.001, 'height_edge': -0.032, 'attacker_skill': 0.8893, 'defender_skill': 0.8915, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Ryan Gravenberch', 'market_value': 81000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8915}], 'xg_override': 0.0769}	aerialWon: 0.9279 -> 1.1 totalShots: 1.024 -> 0.9743 shotOffTarget: 0.7029 -> 0.6688 onTargetScoringAttempt: 0.3211 -> 0.3055 expectedGoalsOnTarget: 0.1695 -> 0.1613 bigChanceMissed: 0.1347 -> 0.1282
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.1143 -> 0.104
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 86.0)	`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=0.0694` `goal_rate=0.089` `scorer_weight=0.0788`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0988` `assist_rate=0.0989` `provider_weight=0.0943`	-

Noni Madueke F 74 0 0.12 0.04 178% 2 0.9 6.9 40.5 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 1.0130, quality 0.817)	`market_value_eur=48000000` `quality_factor=0.8168` `boost_factor=1.013` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0018)	`blend_weight=0.0018` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=0.8197` `prior_reliability=0.02` `competition=Premier League`	-
`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': 'Ronald Araújo, Jérémy Jacquet', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9427, 'skill_edge': -0.003, 'height_edge': -0.036, 'attacker_skill': 0.8168, 'defender_skill': 0.8234, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ronald Araújo', 'market_value': 27000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7581}, {'player': 'Jérémy Jacquet', 'market_value': 67000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8886}], 'xg_override': 0.124}	totalShots: 2.0281 -> 1.9119 shotOffTarget: 1.4185 -> 1.3372 onTargetScoringAttempt: 0.6096 -> 0.5747 goals: 0.1589 -> 0.1498 expectedGoals: 0.1315 -> 0.124
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.124 -> 0.116 expected_assists: 0.1219 -> 0.1109
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 80.0)	`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=0.1095` `goal_rate=0.1498` `scorer_weight=0.1332`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.105` `assist_rate=0.0315` `provider_weight=0.0887`	-

Martin Ødegaard M 83 0 0.20 0.10 103% 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': 'Miloš Kerkez', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.498, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 1.0272, 'skill_edge': 0.0265, 'height_edge': -0.008, 'attacker_skill': 0.8879, 'defender_skill': 0.829, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Miloš Kerkez', 'market_value': 36000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.829}], 'xg_override': 0.2141}	aerialWon: 0.0502 -> 1.0 totalShots: 1.9598 -> 2.0131 shotOffTarget: 1.1923 -> 1.2247 onTargetScoringAttempt: 0.7627 -> 0.7834 goals: 0.2787 -> 0.2863 expectedGoals: 0.2084 -> 0.2141
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.2141 -> 0.2002 expected_assists: 0.2063 -> 0.1877
`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=0.1814` `goal_rate=0.2863` `scorer_weight=0.2502`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1711` `assist_rate=0.2328` `provider_weight=0.2071`	-

Eberechi Eze M 71 0 0.10 0.08 ok 1 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': 'Ryan Gravenberch, Alexis Mac Allister', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.209, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.9538, 'skill_edge': -0.0115, 'height_edge': -0.02, 'attacker_skill': 0.865, 'defender_skill': 0.8904, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Ryan Gravenberch', 'market_value': 81000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8915}, {'player': 'Alexis Mac Allister', 'market_value': 77000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8893}], 'xg_override': 0.1089}	aerialWon: 0.3971 -> 1.0 totalShots: 1.5033 -> 1.4338 shotOffTarget: 1.0325 -> 0.9848 onTargetScoringAttempt: 0.4703 -> 0.4486 expectedGoalsOnTarget: 0.2375 -> 0.2265 goals: 0.1165 -> 0.1111 expectedGoals: 0.1142 -> 0.1089
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1089 -> 0.1018 expected_assists: 0.077 -> 0.0701
`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=0.0968` `goal_rate=0.1111` `scorer_weight=0.1032`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0677` `assist_rate=0.0703` `provider_weight=0.0664`	-

Kai Havertz F 75 1 0.32 0.21 50% 2 1.2 6.8 49.3 26 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 1.0206, quality 0.848)	`market_value_eur=58000000` `quality_factor=0.8478` `boost_factor=1.0206` `reference_quality=0.505` `history_matches=20` `history_shrink=0.2`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0173)	`blend_weight=0.0173` `history_matches=20` `season_overlap_discount=1.0` `per90_to_match_factor=0.8356` `prior_reliability=0.1333` `competition=Premier League`	totalOffside: 0.9984 -> 1.0318 totalShots: 2.1953 -> 2.1717 wasFouled: 0.8924 -> 0.9059 totalCross: 0.7531 -> 0.74
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ronald Araújo, Jérémy Jacquet', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.219, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 1.0279, 'skill_edge': 0.011, 'height_edge': 0.008, 'attacker_skill': 0.8478, 'defender_skill': 0.8234, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ronald Araújo', 'market_value': 27000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7581}, {'player': 'Jérémy Jacquet', 'market_value': 67000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8886}], 'xg_override': 0.337}	totalShots: 2.1956 -> 2.2569 shotOffTarget: 1.3759 -> 1.4143 onTargetScoringAttempt: 0.8197 -> 0.8426 bigChanceMissed: 0.5905 -> 0.607 expectedGoalsOnTarget: 0.3574 -> 0.3674 expectedGoals: 0.3279 -> 0.337 goals: 0.2755 -> 0.2832
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.30 (squad xG sum 1.3911, xG scale 0.9352, xA scale 0.9100, team xA 1.04 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.301` `squad_xg_sum=1.3911` `squad_xa_sum=1.1438` `team_expected_assists=1.0408` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.337 -> 0.3152 expected_assists: 0.0596 -> 0.0542
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 81.0)	`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=0.2704` `goal_rate=0.2832` `scorer_weight=0.2714`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0528` `assist_rate=0.0695` `provider_weight=0.0591`	-

Team totals 1 1.30 14 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Illan Meslier	G	4.6m	11.9%	Market-value substitute prior
William Saliba	D	15.4m	38.0%	Market-value substitute prior
Jurriën Timber	D	15.3m	37.7%	Market-value substitute prior
Martín Zubimendi	M	18.9m	72.8%	Market-value substitute prior
Max Dowman	M	23.5m	57.0%	Market-value substitute prior
Bukayo Saka	F	27.1m	37.1%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Ryan Gravenberch vs Declan Rice will be the pivotal duel. Total antagonist xG — Home: 1.29, Away: 0.92. 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 49.9% / 50.1%, dominance ratio 0.49, key duel: Ryan Gravenberch vs Declan Rice

Florian Wirtz xG 0.16Alexander Isak xG 0.48Bradley Barcola xG 0.17Martin Ødegaard xG 0.21Eberechi Eze xG 0.11Kai Havertz xG 0.34

Summary

Antagonist matchup analysis for Liverpool vs Arsenal. Most likely scoreline: 2-1. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Liverpool 3W-5D-2L vs Arsenal 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 — Ryan Gravenberch vs Declan Rice will be the pivotal duel. Total antagonist xG — Home: 1.29, Away: 0.92. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Racing Club vs Real Madrid

LaLiga · 20261101 · 4-2-3-1 vs 4-2-3-1

Predicted 0-2Winner: Real MadridWinning H 2-1 (2.9%)Winning A 0-2 (9.5%)Confidence 0.81λ home/away 0.92 / 2.77Most-likely P 9.5%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Racing Club vs Real Madrid. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 0.913, Away 3.316). Final calibrated Poisson lambdas: Home 0.924, Away 2.772 (most likely score 0-2).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.91 / 3.32 Final λ (H/A) 0.92 / 2.77

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Racing Club	Real Madrid
League position	15.00	3.00
Points per game	1.20	2.01
Attack index	1.00	1.30
Defense (concede) index	0.85	1.33
Form multiplier	0.96	1.04
Standing λ multiplier	0.93	1.26

Lambda decomposition (how the goal rates were built)

Stage	Racing Club λ	Real Madrid λ
Pre-mismatch	0.867	3.482
Pre-calibration (Micro-duels)	0.913	3.316
Final λ	0.924	2.772

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	9.5%
1-2	8.8%
0-3	8.8%
1-3	8.2%
0-1	6.9%

Home win	9.8%
Draw	14.3%
Away win	75.8%
Over 2.5	71.4%
BTTS yes	56.6%

Pregame fair line — favorite Real Madrid (75.8%), fair total 3.70, fair spread -1.85

Projected players vs season baseline

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

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

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

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

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9989, quality 0.481)	`market_value_eur=6500000` `quality_factor=0.4805` `boost_factor=0.9989` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0197)	`blend_weight=0.0197` `history_matches=28` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.7086 -> 2.7209 wasFouled: 0.2194 -> 0.2282
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 3.3158}`	-
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	shots_faced: 31.5 -> 26.3 expected_saves: 7.71 -> 6.43 high_pressure_saves: 2.65 -> 2.22
`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_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=1.0403`	-
`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=0.7855`	-

Alvaro Mantilla D 87 0 0.04 0.02 56% 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': '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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	-
`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_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=0.036` `goal_rate=0.0` `scorer_weight=0.0294`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0194` `assist_rate=0.1938` `provider_weight=0.0245`	-

Pablo Ramón D 84 0 0.01 0.01 142% 1 0.2 6.9 39.0 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 0.9922, 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`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0300)	`blend_weight=0.03` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.9354` `prior_reliability=0.12` `competition=La Liga`	wonTackle: 0.966 -> 0.9994 interceptionWon: 1.3422 -> 1.3643 totalShots: 0.5901 -> 0.5724 wasFouled: 1.2286 -> 1.2229
`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': 'Kylian Mbappé', '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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	-
`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=0.0127` `goal_rate=0.0` `scorer_weight=0.0102`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0071` `assist_rate=0.0` `provider_weight=0.0061`	-

Jeanuël Belocian D 90 0 0.08 0.04 101% 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': '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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0849 -> 0.0792
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 71.0)	`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=0.0761` `goal_rate=0.2715` `scorer_weight=0.099`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0072` `assist_rate=0.0` `provider_weight=0.0062`	-

Aarón Martín M 87 0 0.04 - n/a 0 0.0 6.7 21.2 16 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 0.9934, quality 0.461)	`market_value_eur=4900000` `quality_factor=0.4609` `boost_factor=0.9934` `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': 'Marc Cucurella', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.308, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.7468, 'skill_edge': -0.1923, 'height_edge': 0.02, 'attacker_skill': 0.4609, 'defender_skill': 0.8882, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Marc Cucurella', 'market_value': 62000000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.8882}], 'xg_override': 0.0392}	aerialWon: 0.358 -> 1.1 totalShots: 0.5796 -> 0.4328 shotOffTarget: 0.4269 -> 0.3188 onTargetScoringAttempt: 0.1527 -> 0.114 goals: 0.0664 -> 0.0496 expectedGoals: 0.0525 -> 0.0392
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0846 -> 0.0736
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 74.0)	`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=0.0358` `goal_rate=0.0496` `scorer_weight=0.0408`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.071` `assist_rate=0.0937` `provider_weight=0.0786`	-

Iván Martín M 86 0 0.03 0.03 ok 0 0.4 7.1 56.9 34 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9979, 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`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0068)	`blend_weight=0.0068` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9541` `prior_reliability=0.1` `competition=La Liga`	wonTackle: 0.8235 -> 0.8352 totalCross: 0.2829 -> 0.2896
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Aurélien Tchouaméni', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.6456, 'skill_edge': -0.2011, 'height_edge': -0.04, 'attacker_skill': 0.4396, 'defender_skill': 0.8865, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Aurélien Tchouaméni', 'market_value': 73000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8865}], 'xg_override': 0.0274}	totalShots: 0.6618 -> 0.4273 aerialWon: 0.7754 -> 1.0 shotOffTarget: 0.4461 -> 0.288 onTargetScoringAttempt: 0.2144 -> 0.1384 goals: 0.0674 -> 0.0435 expectedGoalsOnTarget: 0.0567 -> 0.0366 expectedGoals: 0.0424 -> 0.0274
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.063 -> 0.0548
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 77.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0252` `goal_rate=0.0435` `scorer_weight=0.0308`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0533` `assist_rate=0.0783` `provider_weight=0.0622`	-

Matteo Prati M 81 0 0.02 0.01 287% 0 0.2 6.9 39.2 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9946, 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`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0072)	`blend_weight=0.0072` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9009` `prior_reliability=0.0267` `competition=La Liga`	interceptionWon: 0.5238 -> 0.5363 fouls: 0.6041 -> 0.616 wonTackle: 1.6075 -> 1.5959 wasFouled: 0.942 -> 0.9352
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Aurélien Tchouaméni', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.21, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.6912, 'skill_edge': -0.1861, 'height_edge': -0.024, 'attacker_skill': 0.473, 'defender_skill': 0.8865, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Aurélien Tchouaméni', 'market_value': 73000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.8865}], 'xg_override': 0.0261}	aerialWon: 0.3767 -> 1.1 totalShots: 0.501 -> 0.3463 shotOffTarget: 0.3765 -> 0.2602 onTargetScoringAttempt: 0.1245 -> 0.0861 goals: 0.0507 -> 0.035 expectedGoals: 0.0377 -> 0.0261
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0403 -> 0.0351
`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=0.024` `goal_rate=0.035` `scorer_weight=0.0271`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0345` `assist_rate=0.0562` `provider_weight=0.0413`	-

Sergio Canales F 79 0 0.08 0.09 ok 2 1.5 7.1 48.1 25 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9935, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.9935` `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=0.8754` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.7414 -> 2.655 totalShots: 1.8875 -> 1.9341 wasFouled: 2.1823 -> 2.1414 interceptionWon: 0.5214 -> 0.5026 wonTackle: 0.5089 -> 0.4905 fouls: 0.7332 -> 0.7194 onTargetScoringAttempt: 0.8146 -> 0.8234 goalAssist: 0.1939 -> 0.1869
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Denzel Dumfries, Dean Huijsen', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.6611, 'skill_edge': -0.1705, 'height_edge': -0.06, 'attacker_skill': 0.4399, 'defender_skill': 0.8189, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Denzel Dumfries', 'market_value': 26000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7498}, {'player': 'Dean Huijsen', 'market_value': 66000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8879}], 'xg_override': 0.082}	totalShots: 1.9341 -> 1.2786 shotOffTarget: 1.0729 -> 0.7093 onTargetScoringAttempt: 0.8234 -> 0.5443 bigChanceMissed: 0.1939 -> 0.1282 expectedGoalsOnTarget: 0.1803 -> 0.1192 goals: 0.166 -> 0.1097 expectedGoals: 0.1241 -> 0.082
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.082 -> 0.0765 expected_assists: 0.1514 -> 0.1317
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0736` `goal_rate=0.1097` `scorer_weight=0.0925`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1234` `assist_rate=0.1869` `provider_weight=0.1549`	-

Pablo García F 74 0 0.09 0.06 47% 1 0.8 6.7 34.0 31 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9998, quality 0.501)	`market_value_eur=8199999` `quality_factor=0.5011` `boost_factor=0.9998` `reference_quality=0.505` `history_matches=24` `history_shrink=0.1724`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0045)	`blend_weight=0.0045` `history_matches=24` `season_overlap_discount=1.0` `per90_to_match_factor=0.8197` `prior_reliability=0.04` `competition=La Liga`	wasFouled: 1.0313 -> 1.0512 fouls: 0.4718 -> 0.4881 totalShots: 1.7763 -> 1.7867 goals: 0.1969 -> 0.2021 totalCross: 1.1399 -> 1.1348
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Denzel Dumfries, Dean Huijsen', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7016, 'skill_edge': -0.143, 'height_edge': -0.06, 'attacker_skill': 0.5011, 'defender_skill': 0.8189, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Denzel Dumfries', 'market_value': 26000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7498}, {'player': 'Dean Huijsen', 'market_value': 66000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8879}], 'xg_override': 0.1005}	totalShots: 1.7867 -> 1.2535 shotOffTarget: 1.1593 -> 0.8134 onTargetScoringAttempt: 0.6204 -> 0.4353 goals: 0.2021 -> 0.1418 bigChanceMissed: 0.1948 -> 0.1367 expectedGoalsOnTarget: 0.1786 -> 0.1253 expectedGoals: 0.1432 -> 0.1005
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1005 -> 0.0937 expected_assists: 0.0669 -> 0.0582
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 70.0)	`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=0.0894` `goal_rate=0.1418` `scorer_weight=0.1171`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0565` `assist_rate=0.0` `provider_weight=0.0466`	-

Iñigo Vicente F 86 0 0.05 0.03 65% 1 0.5 7.2 51.8 24 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 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`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0405)	`blend_weight=0.0405` `history_matches=10` `season_overlap_discount=1.0` `per90_to_match_factor=0.9567` `prior_reliability=0.1867` `competition=La Liga`	totalCross: 5.0983 -> 5.0026 totalShots: 1.0533 -> 1.0246 onTargetScoringAttempt: 0.4239 -> 0.4068 wonTackle: 1.0986 -> 1.0818 interceptionWon: 0.6638 -> 0.6508 fouls: 0.7837 -> 0.7935 wasFouled: 2.2458 -> 2.2379
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Denzel Dumfries, Dean Huijsen', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.6976, 'skill_edge': -0.1517, 'height_edge': -0.054, 'attacker_skill': 0.4818, 'defender_skill': 0.8189, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Denzel Dumfries', 'market_value': 26000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7498}, {'player': 'Dean Huijsen', 'market_value': 66000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8879}], 'xg_override': 0.0552}	totalShots: 1.0362 -> 0.7229 shotOffTarget: 0.6294 -> 0.4391 onTargetScoringAttempt: 0.4068 -> 0.2838 goals: 0.1056 -> 0.0737 expectedGoalsOnTarget: 0.0992 -> 0.0692 expectedGoals: 0.0792 -> 0.0552
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.2773 -> 0.2412
`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=0.0502` `goal_rate=0.0737` `scorer_weight=0.0606`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.2143` `assist_rate=0.3169` `provider_weight=0.2704`	-

Yassir Zabiri F 83 0 0.34 0.35 ok 2 1.6 6.8 51.1 14 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0145, quality 0.650)	`market_value_eur=22000000` `quality_factor=0.6503` `boost_factor=1.0145` `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=0.9209` `prior_reliability=0.0867` `competition=La Liga`	goals: 0.4988 -> 0.5294 totalOffside: 0.2014 -> 0.2242 onTargetScoringAttempt: 1.1981 -> 1.2156 totalShots: 2.6649 -> 2.6814 fouls: 1.2521 -> 1.2685 wasFouled: 0.5442 -> 0.534 wonTackle: 0.5396 -> 0.5295 interceptionWon: 0.3616 -> 0.3548
`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': 'Denzel Dumfries, Dean Huijsen', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8326, 'skill_edge': -0.0759, 'height_edge': -0.038, 'attacker_skill': 0.6503, 'defender_skill': 0.8189, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Denzel Dumfries', 'market_value': 26000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7498}, {'player': 'Dean Huijsen', 'market_value': 66000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8879}], 'xg_override': 0.3698}	totalShots: 2.6824 -> 2.2334 shotOffTarget: 1.4668 -> 1.2213 onTargetScoringAttempt: 1.2156 -> 1.0121 expectedGoalsOnTarget: 0.7432 -> 0.6188 goals: 0.5294 -> 0.4408 expectedGoals: 0.4441 -> 0.3698 bigChanceMissed: 0.224 -> 0.1865
`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 0.92 (squad xG sum 0.9911, xG scale 0.9323, xA scale 0.8699, team xA 0.74 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9911` `squad_xa_sum=0.8498` `team_expected_assists=0.7392` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.3698 -> 0.3447 expected_assists: 0.0526 -> 0.0458
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 66.0)	`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=0.2916` `goal_rate=0.4408` `scorer_weight=0.403`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0448` `assist_rate=0.0` `provider_weight=0.0366`	-

Team totals 0 0.92 10 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Simon Eriksson	G	4.4m	10.9%	Market-value substitute prior
Jorge Salinas	D	13.8m	31.1%	Market-value substitute prior
Facundo González	D	13.6m	29.9%	Market-value substitute prior
Gustavo Puerta	M	22.7m	32.2%	Market-value substitute prior
André Almeida	M	22.1m	50.6%	Market-value substitute prior
Andrés Martín	F	25.5m	57.0%	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

Kylian Mbappé F 89 2 1.29 0.76 71% 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': 'Alvaro Mantilla, Jeanuël Belocian', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.355, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.2278, 'skill_edge': 0.171, 'height_edge': -0.016, 'attacker_skill': 0.9, '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': 0.8703}	totalShots: 3.9289 -> 4.8239 onTargetScoringAttempt: 2.0785 -> 2.552 shotOffTarget: 1.8299 -> 2.2468 bigChanceMissed: 1.2781 -> 1.5693 expectedGoalsOnTarget: 1.1434 -> 1.4039 goals: 0.9862 -> 1.2109 expectedGoals: 0.7088 -> 0.8703
`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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.8703 -> 1.2898 expected_assists: 0.1804 -> 0.3339
`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=0.7247` `goal_rate=1.2109` `scorer_weight=1.6122`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.2839` `assist_rate=0.1516` `provider_weight=0.2922`	-

Jude Bellingham M 83 0 0.28 0.15 78% 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': 'Iván Martín, Matteo Prati', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.471, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.3403, 'skill_edge': 0.1995, 'height_edge': 0.032, 'attacker_skill': 0.8996, 'defender_skill': 0.4563, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Iván Martín', 'market_value': 2700000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4396}, {'player': 'Matteo Prati', 'market_value': 5000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.473}], 'xg_override': 0.1859}	aerialWon: 0.6141 -> 1.2 totalShots: 1.693 -> 2.2691 shotOffTarget: 1.0936 -> 1.4658 onTargetScoringAttempt: 0.5956 -> 0.7983 expectedGoalsOnTarget: 0.1937 -> 0.2596 goals: 0.1601 -> 0.2146 expectedGoals: 0.1387 -> 0.1859 bigChanceMissed: 0.1282 -> 0.1718
`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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1859 -> 0.2755 expected_assists: 0.1378 -> 0.2551
`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=0.2408` `goal_rate=0.2146` `scorer_weight=0.309`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1327` `provider_weight=0.2482`	-

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': 'Yassir Zabiri, Pablo García', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.913}`	-
`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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	shots_faced: 8.7 -> 8.8 expected_saves: 2.13 -> 2.16 high_pressure_saves: 0.73 -> 0.74
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 90.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=3.1623`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=1.7856`	-

Denzel Dumfries D 85 0 0.10 0.03 249% 0 0.5 6.6 35.2 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 1.0209, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0209` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0317)	`blend_weight=0.0317` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.9487` `prior_reliability=0.1267` `competition=La Liga`	totalShots: 0.4178 -> 0.4845 wonTackle: 0.9635 -> 0.9962 fouls: 0.3127 -> 0.3344 interceptionWon: 0.5685 -> 0.5821 totalCross: 0.771 -> 0.7782
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yassir Zabiri', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0642 -> 0.0951 expected_assists: 0.0324 -> 0.06
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 18 by projected rating, fifa_overall 83.0)	`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0907` `goal_rate=0.0` `scorer_weight=0.0761`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0` `provider_weight=0.048`	-

Ibrahima Konaté D 89 0 0.05 0.02 102% 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': 'Iñigo Vicente', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0323 -> 0.0479 expected_assists: 0.0095 -> 0.0176
`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=0.0468` `goal_rate=0.0042` `scorer_weight=0.0383`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0174` `assist_rate=0.0` `provider_weight=0.0148`	-

Dean Huijsen D 84 0 0.10 0.05 94% 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': 'Yassir Zabiri', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0644 -> 0.0954 expected_assists: 0.0283 -> 0.0524
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.091` `goal_rate=0.0206` `scorer_weight=0.0763`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0511` `assist_rate=0.0126` `provider_weight=0.0419`	-

Marc Cucurella D 89 0 0.03 0.06 52% 0 0.3 6.7 56.7 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0108, quality 0.857)	`market_value_eur=62000000` `quality_factor=0.8569` `boost_factor=1.0108` `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=0.9856` `prior_reliability=0.12` `competition=La Liga`	fouls: 1.5234 -> 1.5113 totalCross: 1.3477 -> 1.337 wasFouled: 0.7167 -> 0.711
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Aarón Martín', '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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0197 -> 0.0292 expected_assists: 0.0327 -> 0.0605
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 85.0)	`match_squad_rank=17` `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=0.0288` `goal_rate=0.0` `scorer_weight=0.0234`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0587` `assist_rate=0.0476` `provider_weight=0.0714`	-

Aurélien Tchouaméni M 83 0 0.10 0.06 73% 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': 'Iván Martín', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.661, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.3544, 'skill_edge': 0.2011, 'height_edge': 0.04, 'attacker_skill': 0.8865, 'defender_skill': 0.4396, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Iván Martín', 'market_value': 2700000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4396}], 'xg_override': 0.0702}	totalShots: 0.837 -> 1.1336 shotOffTarget: 0.6569 -> 0.8897 aerialWon: 1.2886 -> 1.2 onTargetScoringAttempt: 0.1801 -> 0.2439 expectedGoals: 0.0518 -> 0.0702 goals: 0.0489 -> 0.0662 bigChanceMissed: 0.04 -> 0.0542 expectedGoalsOnTarget: 0.0347 -> 0.047
`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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0702 -> 0.104 expected_assists: 0.041 -> 0.0759
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 84.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.0988` `goal_rate=0.0662` `scorer_weight=0.1005`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0731` `assist_rate=0.0579` `provider_weight=0.09`	-

Bernardo Silva M 78 0 0.10 0.08 ok 1 0.8 6.9 58.2 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 1.0040, 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 0.0085)	`blend_weight=0.0085` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=0.8703` `prior_reliability=0.1333` `competition=La Liga`	interceptionWon: 0.8982 -> 0.9054
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 'CDM vs CDM', 'duel_win_rate': 0.506, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1261, 'skill_edge': 0.1058, 'height_edge': -0.02, 'attacker_skill': 0.6747, 'defender_skill': 0.4396, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Iván Martín', 'market_value': 2700000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4396}], 'xg_override': 0.0662}	aerialWon: 0.1658 -> 0.9 totalShots: 0.5624 -> 0.6334 shotOffTarget: 0.424 -> 0.4775 onTargetScoringAttempt: 0.1384 -> 0.1559 expectedGoals: 0.0588 -> 0.0662 goals: 0.0575 -> 0.0648 expectedGoalsOnTarget: 0.0493 -> 0.0555
`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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0662 -> 0.0981 expected_assists: 0.0892 -> 0.1651
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0934` `goal_rate=0.0648` `scorer_weight=0.0969`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1522` `assist_rate=0.0851` `provider_weight=0.1602`	-

Arda Güler M 74 0 0.31 0.11 169% 2 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': 'Julen Agirrezabala', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.533, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.166, 'skill_edge': 0.1569, 'height_edge': -0.044, 'attacker_skill': 0.8922, 'defender_skill': 0.5436, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Julen Agirrezabala', 'market_value': 6500000, 'role': 'GK', 'price_index': 0.55, 'adjusted_quality': 0.5436}], 'xg_override': 0.208}	aerialWon: 0.2778 -> 0.9 totalShots: 1.9559 -> 2.2806 shotOffTarget: 1.2365 -> 1.4418 onTargetScoringAttempt: 0.7194 -> 0.8388 goals: 0.1788 -> 0.2085 expectedGoals: 0.1784 -> 0.208 expectedGoalsOnTarget: 0.1261 -> 0.147 bigChanceMissed: 0.106 -> 0.1236
`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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.208 -> 0.3083 expected_assists: 0.1926 -> 0.3565
`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=0.2653` `goal_rate=0.2085` `scorer_weight=0.3089`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.2999` `assist_rate=0.1794` `provider_weight=0.3371`	-

Yan Diomande F 84 0 0.27 0.07 297% 2 0.8 7.1 58.8 16 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 1.0394, quality 0.899)	`market_value_eur=132000000` `quality_factor=0.8986` `boost_factor=1.0394` `reference_quality=0.505` `history_matches=10` `history_shrink=0.3333`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0101)	`blend_weight=0.0101` `history_matches=10` `season_overlap_discount=1.0` `per90_to_match_factor=0.9386` `prior_reliability=0.0467` `competition=La Liga`	totalCross: 2.5219 -> 2.5506 wonTackle: 1.8201 -> 1.8017 totalShots: 1.673 -> 1.6561 fouls: 1.2052 -> 1.193 wasFouled: 1.1578 -> 1.1461 interceptionWon: 0.9832 -> 0.9733 onTargetScoringAttempt: 0.6028 -> 0.5967
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 0.354, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.2269, 'skill_edge': 0.1704, 'height_edge': -0.016, 'attacker_skill': 0.8986, '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': 0.179}	totalShots: 1.6669 -> 2.0451 shotOffTarget: 1.0702 -> 1.313 onTargetScoringAttempt: 0.5967 -> 0.7321 bigChanceMissed: 0.3636 -> 0.4461 expectedGoalsOnTarget: 0.2421 -> 0.297 goals: 0.2204 -> 0.2704 expectedGoals: 0.1459 -> 0.179
`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 2.77 (squad xG sum 1.8704, xG scale 1.4820, xA scale 1.8511, team xA 1.80 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=2.772` `squad_xg_sum=1.8704` `squad_xa_sum=0.9733` `team_expected_assists=1.8018` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.179 -> 0.2653 expected_assists: 0.1602 -> 0.2966
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.233` `goal_rate=0.2704` `scorer_weight=0.3316`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.2567` `assist_rate=0.4062` `provider_weight=0.3707`	-

Team totals 2 2.77 16 7.0

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
Álvaro Carreras	D	15.1m	24.9%	Market-value substitute prior
Federico Valverde	M	23.8m	34.3%	Market-value substitute prior
Eduardo Camavinga	M	17.2m	59.4%	Market-value substitute prior
Vinícius Júnior	F	27.1m	37.1%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~55% possession expected (Matteo Prati vs Jude Bellingham). Total antagonist xG — Home: 0.70, Away: 1.58. 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 45.2% / 54.8%, dominance ratio 0.35, key duel: Matteo Prati vs Jude Bellingham

Aarón Martín xG 0.04Yassir Zabiri xG 0.37Sergio Canales xG 0.08Arda Güler xG 0.21Jude Bellingham xG 0.19Kylian Mbappé xG 0.87

Summary

Antagonist matchup analysis for Racing Club vs Real Madrid. Most likely scoreline: 0-2. Lambdas derived from 7 home and 6 away individual player duels. Head-to-head: Racing Club 0W-1D-9L vs Real Madrid over 10 meetings.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~55% possession expected (Matteo Prati vs Jude Bellingham). Total antagonist xG — Home: 0.70, Away: 1.58. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Athletic Club vs Real Sociedad

LaLiga · 20261101 · 4-2-3-1 vs 4-2-3-1

Predicted 2-1Winner: Athletic ClubWinning H 2-1 (9.5%)Winning A 1-2 (6.9%)Confidence 0.74λ home/away 1.73 / 1.25Most-likely P 9.5%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Athletic Club vs Real Sociedad. 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 1.269, Away 1.071). Final calibrated Poisson lambdas: Home 1.729, Away 1.255 (most likely score 2-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.27 / 1.07 Final λ (H/A) 1.73 / 1.25

FBref Team Priors: Athletic Club (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.556) vs Real Sociedad (Gls/90: 0.75, GA/90: 0.75 → E[λ]: 0.556) | 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	Athletic Club	Real Sociedad
League position	7.00	5.00
Points per game	1.35	1.70
Attack index	1.00	1.12
Defense (concede) index	1.09	0.90
Form multiplier	0.98	1.02
Standing λ multiplier	1.03	1.01

Lambda decomposition (how the goal rates were built)

Stage	Athletic Club λ	Real Sociedad λ
FBref Squad Prior E[λ] (weight 0.228)	0.556	0.556
Pre-competitive-floor	1.396	1.039
Pre-calibration (Micro-duels)	1.269	1.071
Final λ	1.729	1.255

competition calibration scale 1.225competition 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	11.1%
2-1	9.5%
1-0	8.7%
2-0	7.6%
1-2	6.9%

Home win	48.5%
Draw	23.8%
Away win	27.8%
Over 2.5	57.3%
BTTS yes	58.9%

Pregame fair line — favorite Athletic Club (48.5%), fair total 2.98, fair spread 0.47

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.

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': 'Mikel Oyarzabal, Gonçalo Guedes', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.0708}`	-
`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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	shots_faced: 10.2 -> 11.9 expected_saves: 2.5 -> 2.91 high_pressure_saves: 0.86 -> 1.0
`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: 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=1.9109`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=1.1843`	-

Hugo Rincón D 80 0 0.05 0.01 302% 0 0.2 6.7 48.2 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 0.9978, quality 0.442)	`market_value_eur=3400000` `quality_factor=0.4424` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0060)	`blend_weight=0.006` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.8864` `prior_reliability=0.08` `competition=La Liga`	wonTackle: 1.0874 -> 1.0808
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Mikel Oyarzabal', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.0296 -> 0.0511 expected_assists: 0.0568 -> 0.0981
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 75.0)	`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=0.0498` `goal_rate=0.0782` `scorer_weight=0.0639`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0934` `assist_rate=0.0304` `provider_weight=0.0785`	-

Aymeric Laporte D 85 0 0.09 0.07 37% 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': 'Mikel Oyarzabal', '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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.0528 -> 0.0911 expected_assists: 0.0142 -> 0.0245
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 84.0)	`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=0.0871` `goal_rate=0.0` `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=0.0242` `assist_rate=0.0031` `provider_weight=0.0203`	-

Dani Vivian D 79 0 0.04 0.02 124% 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': 'Mikel Oyarzabal', '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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.0239 -> 0.0413 expected_assists: 0.0281 -> 0.0485
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 78.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0405` `goal_rate=0.0578` `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=0.0473` `assist_rate=0.0` `provider_weight=0.0388`	-

Yuri Berchiche D 78 0 0.08 0.02 245% 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': 'Carlos Soler', '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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.0476 -> 0.0822 expected_assists: 0.1455 -> 0.2511
`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=0.0789` `goal_rate=0.0` `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=0.2221` `assist_rate=0.1268` `provider_weight=0.2271`	-

Mikel Jauregizar M 70 0 0.13 0.03 345% 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': 'Beñat Turrientes', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.489, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1013, 'skill_edge': 0.0769, 'height_edge': -0.008, 'attacker_skill': 0.7219, 'defender_skill': 0.551, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Beñat Turrientes', 'market_value': 10600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.551}], 'xg_override': 0.0755}	aerialWon: 1.65 -> 1.0 totalShots: 0.9626 -> 1.0601 shotOffTarget: 0.6842 -> 0.7535 onTargetScoringAttempt: 0.2784 -> 0.3066 expectedGoals: 0.0686 -> 0.0755 goals: 0.0554 -> 0.061
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.0755 -> 0.1303 expected_assists: 0.0531 -> 0.0917
`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_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=0.1222` `goal_rate=0.061` `scorer_weight=0.1153`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0876` `assist_rate=0.0561` `provider_weight=0.0944`	-

Beñat Gerenabarrena M 79 0 0.05 0.00 2138% 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': 'Beñat Turrientes', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.362, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.915, 'skill_edge': -0.0338, 'height_edge': -0.024, 'attacker_skill': 0.4759, 'defender_skill': 0.551, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Beñat Turrientes', 'market_value': 10600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.551}], 'xg_override': 0.0311}	aerialWon: 0.6976 -> 0.9 totalShots: 0.4711 -> 0.4311 shotOffTarget: 0.3233 -> 0.2958 onTargetScoringAttempt: 0.1478 -> 0.1352
`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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.0311 -> 0.0537 expected_assists: 0.0444 -> 0.0766
`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=0.0523` `goal_rate=0.0399` `scorer_weight=0.0595`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0737` `assist_rate=0.0595` `provider_weight=0.0889`	-

Álex Berenguer F 80 0 0.22 0.13 72% 1 1.2 6.9 53.9 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 0.9982, quality 0.451)	`market_value_eur=4099999` `quality_factor=0.4511` `boost_factor=0.9982` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0111)	`blend_weight=0.0111` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.8869` `prior_reliability=0.1533` `competition=La Liga`	wasFouled: 1.1022 -> 1.0943 totalCross: 6.0045 -> 6.0106
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mamadou Sarr, Jon Martin', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.7289, 'skill_edge': -0.1264, 'height_edge': -0.058, 'attacker_skill': 0.4511, 'defender_skill': 0.732, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mamadou Sarr', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}, {'player': 'Jon Martin', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}], 'xg_override': 0.1248}	totalShots: 1.7372 -> 1.2662 shotOffTarget: 1.1108 -> 0.8097 onTargetScoringAttempt: 0.626 -> 0.4563 expectedGoalsOnTarget: 0.2634 -> 0.192 goals: 0.2471 -> 0.1801 expectedGoals: 0.1712 -> 0.1248 bigChanceMissed: 0.1071 -> 0.0781
`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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.1248 -> 0.2154 expected_assists: 0.1335 -> 0.2305
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1938` `goal_rate=0.1801` `scorer_weight=0.2692`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.2059` `assist_rate=0.1628` `provider_weight=0.2673`	-

Maroan Sannadi F 68 0 0.26 0.04 587% 1 0.4 6.6 32.4 16 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9952, quality 0.437)	`market_value_eur=2800000` `quality_factor=0.4374` `boost_factor=0.9952` `reference_quality=0.505` `history_matches=16` `history_shrink=0.2381`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0041)	`blend_weight=0.0041` `history_matches=16` `season_overlap_discount=1.0` `per90_to_match_factor=0.7569` `prior_reliability=0.0267` `competition=La Liga`	totalShots: 1.6905 -> 1.6835
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mamadou Sarr, Jon Martin', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.8198, 'skill_edge': -0.1326, 'height_edge': 0.01, 'attacker_skill': 0.4374, 'defender_skill': 0.732, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mamadou Sarr', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}, {'player': 'Jon Martin', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}], 'xg_override': 0.1531}	totalShots: 1.6885 -> 1.3842 shotOffTarget: 1.2123 -> 0.9938 onTargetScoringAttempt: 0.4762 -> 0.3904 expectedGoalsOnTarget: 0.1902 -> 0.1559 expectedGoals: 0.1868 -> 0.1531 goals: 0.1723 -> 0.1413
`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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.1531 -> 0.2643 expected_assists: 0.0204 -> 0.0352
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 77.0)	`match_squad_rank=17` `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=0.2323` `goal_rate=0.1413` `scorer_weight=0.2489`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0346` `assist_rate=0.0` `provider_weight=0.0282`	-

Nico Williams F 71 1 0.27 0.13 116% 2 1.6 7.0 57.8 28 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0117, quality 0.800)	`market_value_eur=44000000` `quality_factor=0.8002` `boost_factor=1.0117` `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=0.7934` `prior_reliability=0.08` `competition=La Liga`	fouls: 1.4097 -> 1.4001 wasFouled: 0.9107 -> 0.9045
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mamadou Sarr, Jon Martin', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.193, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.9893, 'skill_edge': 0.0307, 'height_edge': -0.038, 'attacker_skill': 0.8002, 'defender_skill': 0.732, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mamadou Sarr', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}, {'player': 'Jon Martin', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}], 'xg_override': 0.1568}	totalShots: 2.0092 -> 1.9877 shotOffTarget: 1.4326 -> 1.4173 onTargetScoringAttempt: 0.5685 -> 0.5624
`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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.1568 -> 0.2707 expected_assists: 0.1086 -> 0.1875
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2372` `goal_rate=0.183` `scorer_weight=0.305`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.171` `assist_rate=0.0723` `provider_weight=0.15`	-

Iñaki Williams F 67 1 0.45 0.19 131% 2 1.5 6.8 53.6 37 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9995, quality 0.490)	`market_value_eur=7300000` `quality_factor=0.4903` `boost_factor=0.9995` `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=0.7448` `prior_reliability=0.1333` `competition=La Liga`	totalShots: 2.3499 -> 2.3414 onTargetScoringAttempt: 0.8822 -> 0.8882 fouls: 0.894 -> 0.8889
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mamadou Sarr, Jon Martin', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.8195, 'skill_edge': -0.1088, 'height_edge': -0.014, 'attacker_skill': 0.4903, 'defender_skill': 0.732, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mamadou Sarr', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}, {'player': 'Jon Martin', 'market_value': 24000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.732}], 'xg_override': 0.2584}	totalShots: 2.3559 -> 1.9307 shotOffTarget: 1.4677 -> 1.2028 onTargetScoringAttempt: 0.8882 -> 0.7279 goals: 0.4127 -> 0.3382 bigChanceMissed: 0.349 -> 0.286 expectedGoals: 0.3153 -> 0.2584 expectedGoalsOnTarget: 0.276 -> 0.2262
`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 1.73 (squad xG sum 1.0016, xG scale 1.7263, xA scale 1.7263, team xA 1.22 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.729` `squad_xg_sum=1.0016` `squad_xa_sum=0.7085` `team_expected_assists=1.2231` `team_xa_to_xg_ratio=0.7074`	expected_goals: 0.2584 -> 0.4461 expected_assists: 0.0506 -> 0.0873
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 80.0)	`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=0.3599` `goal_rate=0.3382` `scorer_weight=0.5576`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0836` `assist_rate=0.2595` `provider_weight=0.1091`	-

Team totals 2 1.73 11 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
Oihan Sancet	M	22.9m	32.6%	Market-value substitute prior
Beñat Prados	M	22.6m	52.5%	Market-value substitute prior
Robert Navarro	F	25.5m	56.9%	Market-value substitute prior

Real Sociedad — 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

Álex Remiro G 90 0 0.00 - n/a 0.0 7.1 62.2 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 1.0004, quality 0.518)	`market_value_eur=9600000` `quality_factor=0.5177` `boost_factor=1.0004` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0170)	`blend_weight=0.017` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2667` `competition=La Liga`	saves: 2.978 -> 2.9996
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Iñaki Williams, Nico Williams', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2686}`	-
`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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	shots_faced: 12.1 -> 16.4 expected_saves: 2.97 -> 4.01 high_pressure_saves: 1.01 -> 1.38
`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: 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=1.3959`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.8785`	-

Jon Aramburu D 86 0 0.01 0.04 63% 1 0.4 6.7 59.9 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 1.0019, quality 0.567)	`market_value_eur=13900000` `quality_factor=0.5671` `boost_factor=1.0019` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0163)	`blend_weight=0.0163` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9573` `prior_reliability=0.24` `competition=La Liga`	fouls: 2.793 -> 2.8254 interceptionWon: 1.2068 -> 1.239 wonTackle: 1.6201 -> 1.6283 wasFouled: 1.6968 -> 1.7038
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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 Berenguer', '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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 77.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0137` `goal_rate=0.0045` `scorer_weight=0.0117`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0231` `assist_rate=0.0` `provider_weight=0.0187`	-

Mamadou Sarr D 87 0 0.07 0.03 159% 0 0.1 6.8 25.1 21 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 1.0189, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0189` `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': 'Nico Williams', '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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	-
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0642` `goal_rate=0.0` `scorer_weight=0.0531`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0077` `assist_rate=0.0` `provider_weight=0.0066`	-

Jon Martin D 90 0 0.07 0.06 ok 1 0.4 7.0 53.2 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 1.0063, 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 0.0222)	`blend_weight=0.0222` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2667` `competition=La Liga`	interceptionWon: 1.2874 -> 1.2643 wonTackle: 0.8433 -> 0.8579 fouls: 1.411 -> 1.4019
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Nico Williams', '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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	-
`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=0.0684` `goal_rate=0.1736` `scorer_weight=0.0885`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0085` `assist_rate=0.126` `provider_weight=0.0106`	-

Sergio Gómez D 86 0 0.01 0.02 ok 1 0.4 6.8 59.3 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 1.0021, quality 0.575)	`market_value_eur=14600000` `quality_factor=0.5748` `boost_factor=1.0021` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0165)	`blend_weight=0.0165` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9584` `prior_reliability=0.2533` `competition=La Liga`	totalCross: 4.2214 -> 4.2474 wasFouled: 0.339 -> 0.3334 fouls: 0.4172 -> 0.4228
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Maroan Sannadi', '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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	-
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0128` `goal_rate=0.0` `scorer_weight=0.0103`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.116` `provider_weight=0.1078`	-

Beñat Turrientes M 78 0 0.07 0.03 164% 1 0.6 6.9 49.7 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 1.0010, quality 0.529)	`market_value_eur=10600000` `quality_factor=0.5295` `boost_factor=1.001` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0170)	`blend_weight=0.017` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.8618` `prior_reliability=0.1933` `competition=La Liga`	fouls: 0.6634 -> 0.6521 wasFouled: 0.9162 -> 0.9057 onTargetScoringAttempt: 0.3734 -> 0.3824 interceptionWon: 0.435 -> 0.4276 wonTackle: 0.8128 -> 0.8192
`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': 'Mikel Jauregizar', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.351, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.8987, 'skill_edge': -0.0769, 'height_edge': 0.008, 'attacker_skill': 0.551, 'defender_skill': 0.7219, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Mikel Jauregizar', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}], 'xg_override': 0.0693}	aerialWon: 0.2815 -> 1.0 totalShots: 1.0695 -> 0.9612 shotOffTarget: 0.6871 -> 0.6175 onTargetScoringAttempt: 0.3824 -> 0.3437 expectedGoalsOnTarget: 0.1996 -> 0.1794 goals: 0.0873 -> 0.0785 expectedGoals: 0.0771 -> 0.0693
`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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	-
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0646` `goal_rate=0.0785` `scorer_weight=0.072`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0703` `assist_rate=0.0667` `provider_weight=0.0677`	-

Jon Gorrotxategi M 78 0 0.03 0.01 378% 0 0.1 6.9 50.0 27 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0068, quality 0.694)	`market_value_eur=27000000` `quality_factor=0.6941` `boost_factor=1.0068` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0015)	`blend_weight=0.0015` `history_matches=37` `season_overlap_discount=1.0` `per90_to_match_factor=0.8701` `prior_reliability=0.02` `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': 'Mikel Jauregizar', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.424, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0056, 'skill_edge': 0.0038, 'height_edge': 0.0, 'attacker_skill': 0.7304, 'defender_skill': 0.7219, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Mikel Jauregizar', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}], 'xg_override': 0.0325}	aerialWon: 0.9891 -> 1.0
`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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 79.0)	`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=0.0309` `goal_rate=0.0454` `scorer_weight=0.0363`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0342` `assist_rate=0.0453` `provider_weight=0.0385`	-

Luka Sučić M 81 0 0.15 0.09 64% 2 1.2 6.9 55.4 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 1.0037, quality 0.593)	`market_value_eur=16300000` `quality_factor=0.5932` `boost_factor=1.0037` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0187)	`blend_weight=0.0187` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=0.9029` `prior_reliability=0.2067` `competition=La Liga`	totalCross: 1.0135 -> 1.0272 interceptionWon: 0.6075 -> 0.5962 totalShots: 1.671 -> 1.6774
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mikel Jauregizar, Beñat Gerenabarrena', 'matchup_zone': 'Attacking Mid vs Double Pivot — Tight Space Battle', 'duel_win_rate': 0.281, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.061, 'skill_edge': 0.0015, 'height_edge': 0.04, 'attacker_skill': 0.6022, 'defender_skill': 0.5989, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Mikel Jauregizar', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}, {'player': 'Beñat Gerenabarrena', 'market_value': 5200000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4759}], 'xg_override': 0.1567}	aerialWon: 0.4427 -> 1.2 totalShots: 1.6774 -> 1.7797 shotOffTarget: 1.1072 -> 1.1747 onTargetScoringAttempt: 0.5641 -> 0.5985 expectedGoalsOnTarget: 0.2826 -> 0.2998 bigChanceMissed: 0.1874 -> 0.1988 goals: 0.1523 -> 0.1616 expectedGoals: 0.1477 -> 0.1567
`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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	expected_goals: 0.1567 -> 0.1512
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1403` `goal_rate=0.1616` `scorer_weight=0.1548`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.113` `assist_rate=0.1376` `provider_weight=0.129`	-

Carlos Soler M 84 0 0.13 0.09 55% 1 0.8 7.1 59.6 33 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9993, quality 0.482)	`market_value_eur=6600000` `quality_factor=0.4818` `boost_factor=0.9993` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0106)	`blend_weight=0.0106` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9369` `prior_reliability=0.1533` `competition=La Liga`	totalShots: 1.4607 -> 1.4495 wonTackle: 0.2835 -> 0.2934
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.496, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0234, 'skill_edge': 0.0199, 'height_edge': -0.004, 'attacker_skill': 0.4818, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Yuri Berchiche', 'market_value': 910000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.1374}	aerialWon: 0.1221 -> 1.1 totalShots: 1.456 -> 1.4901 shotOffTarget: 1.0179 -> 1.0417 onTargetScoringAttempt: 0.4381 -> 0.4484
`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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	expected_assists: 0.1665 -> 0.1607
`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=0.1241` `goal_rate=0.1472` `scorer_weight=0.1394`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1485` `assist_rate=0.1262` `provider_weight=0.1308`	-

Gonçalo Guedes F 76 0 0.21 0.13 60% 2 1.6 7.0 58.2 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9989, quality 0.471)	`market_value_eur=5700000` `quality_factor=0.4708` `boost_factor=0.9989` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0028)	`blend_weight=0.0028` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.8418` `prior_reliability=0.04` `competition=La Liga`	totalShots: 2.1061 -> 2.1258 onTargetScoringAttempt: 0.8021 -> 0.8127
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 0.865, 'skill_edge': -0.0598, 'height_edge': -0.032, 'attacker_skill': 0.4708, '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': 0.2226}	totalShots: 2.1258 -> 1.8388 shotOffTarget: 1.304 -> 1.128 onTargetScoringAttempt: 0.8127 -> 0.703 bigChanceMissed: 0.3962 -> 0.3427 goals: 0.3402 -> 0.2943 expectedGoals: 0.2573 -> 0.2226 expectedGoalsOnTarget: 0.2522 -> 0.2182
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	expected_goals: 0.2226 -> 0.2147
`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_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=0.1932` `goal_rate=0.2943` `scorer_weight=0.2684`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1231` `assist_rate=0.2343` `provider_weight=0.1642`	-

Mikel Oyarzabal F 82 1 0.28 0.32 ok 2 1.6 7.1 62.8 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 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 0.0133)	`blend_weight=0.0133` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9091` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 1.2792 -> 1.2904 wonTackle: 0.7353 -> 0.7255 goalAssist: 0.119 -> 0.1255 goals: 0.4055 -> 0.4001
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 0.217, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0246, 'skill_edge': 0.0407, 'height_edge': -0.024, 'attacker_skill': 0.6941, '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': 0.2938}	totalShots: 2.2955 -> 2.352 shotOffTarget: 1.3968 -> 1.4312 onTargetScoringAttempt: 0.8987 -> 0.9208 bigChanceMissed: 0.4844 -> 0.4963 goals: 0.4001 -> 0.4099 expectedGoals: 0.2867 -> 0.2938 expectedGoalsOnTarget: 0.2834 -> 0.2904
`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 1.25 (squad xG sum 1.3010, xG scale 0.9646, xA scale 0.9646, team xA 0.85 = 0.67 x lambda)	`scoreline_reset=true` `team_lambda=1.255` `squad_xg_sum=1.301` `squad_xa_sum=0.8767` `team_expected_assists=0.8457` `team_xa_to_xg_ratio=0.6739`	expected_goals: 0.2938 -> 0.2835
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 90.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2469` `goal_rate=0.4099` `scorer_weight=0.3544`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1034` `assist_rate=0.1255` `provider_weight=0.1174`	-

Team totals 1 1.25 13 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Unai Marrero	G	4.4m	10.9%	Market-value substitute prior
Héctor Fort	D	14.1m	32.3%	Market-value substitute prior
Igor Zubeldia	D	24.9m	31.6%	Market-value substitute prior
Arsen Zakharyan	M	12.2m	69.8%	Market-value substitute prior
Brais Méndez	M	22.2m	50.9%	Market-value substitute prior
Takefusa Kubo	F	18.9m	44.7%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Mikel Jauregizar vs Jon Gorrotxategi will be the pivotal duel. Total antagonist xG — Home: 0.80, Away: 0.91. 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 49.8% / 50.2%, dominance ratio 0.48, key duel: Mikel Jauregizar vs Jon Gorrotxategi

Nico Williams xG 0.16Álex Berenguer xG 0.12Maroan Sannadi xG 0.15Carlos Soler xG 0.14Luka Sučić xG 0.16Mikel Oyarzabal xG 0.29

Summary

Antagonist matchup analysis for Athletic Club vs Real Sociedad. Most likely scoreline: 2-1. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Athletic Club 4W-2D-4L vs Real Sociedad 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 — Mikel Jauregizar vs Jon Gorrotxategi will be the pivotal duel. Total antagonist xG — Home: 0.80, Away: 0.91. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Getafe vs Sevilla

LaLiga · 20261101 · 5-3-2 vs 4-4-2

Predicted 1-2Winner: SevillaWinning H 2-1 (7.4%)Winning A 1-2 (9.2%)Confidence 0.72λ home/away 1.33 / 1.66Most-likely P 9.2%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Getafe vs Sevilla. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 5-3-2 vs 4-4-2 (duel lambdas: Home 0.981, Away 1.293). Final calibrated Poisson lambdas: Home 1.326, Away 1.658 (most likely score 1-2).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (6 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.98 / 1.29 Final λ (H/A) 1.33 / 1.66

FBref Team Priors: Getafe (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.494) vs Sevilla (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 0.489) | 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	Getafe	Sevilla
League position	18.00	6.00
Points per game	1.07	1.57
Attack index	0.70	1.03
Defense (concede) index	1.03	1.00
Form multiplier	0.97	1.03
Standing λ multiplier	0.87	1.02

Lambda decomposition (how the goal rates were built)

Stage	Getafe λ	Sevilla λ
FBref Squad Prior E[λ] (weight 0.228)	0.494	0.489
Pre-competitive-floor	0.932	1.452
Pre-calibration (Micro-duels)	0.981	1.293
Final λ	1.326	1.658

competition calibration scale 1.252competition 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%
1-2	9.2%
0-1	8.3%
2-1	7.4%
0-2	7.0%

Home win	30.6%
Draw	24.2%
Away win	45.2%
Over 2.5	57.3%
BTTS yes	59.5%

Pregame fair line — favorite Sevilla (45.2%), 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.

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

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

Enes Ünal F 87 0 0.29 0.09 233% 2 0.7 6.7 45.5 30 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9991, quality 0.484)	`market_value_eur=6800000` `quality_factor=0.4842` `boost_factor=0.9991` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0150)	`blend_weight=0.015` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=0.9662` `prior_reliability=0.1667` `competition=La Liga`	wonTackle: 0.8121 -> 0.829 totalOffside: 0.358 -> 0.3701 wasFouled: 1.427 -> 1.4172 totalShots: 1.9243 -> 1.9186
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Andrés Castrin, Kike Salas', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9191, 'skill_edge': -0.047, 'height_edge': -0.008, 'attacker_skill': 0.4842, 'defender_skill': 0.5887, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Andrés Castrin', 'market_value': 8700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5411}, {'player': 'Kike Salas', 'market_value': 15400000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6363}], 'xg_override': 0.2069}	totalShots: 1.9202 -> 1.7649 shotOffTarget: 1.2622 -> 1.1601 onTargetScoringAttempt: 0.658 -> 0.6048 expectedGoalsOnTarget: 0.2313 -> 0.2126 expectedGoals: 0.2251 -> 0.2069 goals: 0.2223 -> 0.2043
`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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2069 -> 0.2905 expected_assists: 0.0386 -> 0.0574
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 75.0)	`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=0.2521` `goal_rate=0.2043` `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=0.0558` `assist_rate=0.0` `provider_weight=0.0459`	-

Martín Satriano F 77 1 0.28 0.16 75% 2 1.7 6.8 61.8 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 1.0011, quality 0.529)	`market_value_eur=10600000` `quality_factor=0.5295` `boost_factor=1.0011` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0177)	`blend_weight=0.0177` `history_matches=28` `season_overlap_discount=1.0` `per90_to_match_factor=0.8584` `prior_reliability=0.18` `competition=La Liga`	wasFouled: 1.9834 -> 1.9933 interceptionWon: 0.5072 -> 0.4982
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Andrés Castrin, Kike Salas', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9608, 'skill_edge': -0.0266, 'height_edge': 0.0, 'attacker_skill': 0.5295, 'defender_skill': 0.5887, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Andrés Castrin', 'market_value': 8700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5411}, {'player': 'Kike Salas', 'market_value': 15400000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.6363}], 'xg_override': 0.2029}	totalShots: 1.8752 -> 1.8017 shotOffTarget: 1.2798 -> 1.2296 onTargetScoringAttempt: 0.5903 -> 0.5672 expectedGoalsOnTarget: 0.2644 -> 0.254 goals: 0.2299 -> 0.2209 expectedGoals: 0.2112 -> 0.2029
`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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2029 -> 0.2848 expected_assists: 0.0694 -> 0.1032
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 77.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2478` `goal_rate=0.2209` `scorer_weight=0.3051`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0981` `assist_rate=0.119` `provider_weight=0.129`	-

Orel Mangala M 87 0 0.05 0.02 226% 1 0.3 6.8 46.0 10 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0001, quality 0.506)	`market_value_eur=8600000` `quality_factor=0.5059` `boost_factor=1.0001` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0542)	`blend_weight=0.0542` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9683` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 2.4551 -> 2.4095 wasFouled: 0.9361 -> 0.9728 totalCross: 0.4455 -> 0.4214 wonTackle: 0.2326 -> 0.255 totalShots: 0.6875 -> 0.7027 fouls: 2.091 -> 2.1001 onTargetScoringAttempt: 0.1655 -> 0.1565
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Lucien Agoumé', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.338, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8799, 'skill_edge': -0.0537, 'height_edge': -0.028, 'attacker_skill': 0.5172, 'defender_skill': 0.6365, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Lucien Agoumé', 'market_value': 18500000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.6365}], 'xg_override': 0.0385}	aerialWon: 0.3877 -> 1.0 totalShots: 0.7027 -> 0.6183 shotOffTarget: 0.522 -> 0.4593 onTargetScoringAttempt: 0.1565 -> 0.1377 goals: 0.0459 -> 0.0404 expectedGoals: 0.0438 -> 0.0385
`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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0385 -> 0.054 expected_assists: 0.043 -> 0.0639
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0526` `goal_rate=0.0404` `scorer_weight=0.0552`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0619` `assist_rate=0.0541` `provider_weight=0.0715`	-

Ramón Terrats M 71 0 0.17 0.07 137% 1 1.0 6.8 59.2 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 0.9977, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0151)	`blend_weight=0.0151` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.7922` `prior_reliability=0.2` `competition=La Liga`	totalCross: 1.4756 -> 1.5052 totalShots: 1.6917 -> 1.7062 wasFouled: 2.0806 -> 2.0891 fouls: 0.8907 -> 0.8972
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Lucien Agoumé', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.31, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8376, 'skill_edge': -0.0865, 'height_edge': -0.024, 'attacker_skill': 0.4443, 'defender_skill': 0.6365, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Lucien Agoumé', 'market_value': 18500000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.6365}], 'xg_override': 0.1237}	aerialWon: 0.7146 -> 1.0 totalShots: 1.7062 -> 1.4291 shotOffTarget: 1.1508 -> 0.9639 onTargetScoringAttempt: 0.5407 -> 0.4529 bigChanceMissed: 0.1694 -> 0.1419 expectedGoals: 0.1477 -> 0.1237 goals: 0.1412 -> 0.1183 expectedGoalsOnTarget: 0.141 -> 0.1181
`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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1237 -> 0.1737 expected_assists: 0.1031 -> 0.1533
`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=0.1595` `goal_rate=0.1183` `scorer_weight=0.1683`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1421` `assist_rate=0.1068` `provider_weight=0.157`	-

Francho Serrano M 79 0 0.07 0.01 486% 1 0.3 6.8 44.7 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9923, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.9923` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0300)	`blend_weight=0.03` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.8789` `prior_reliability=0.12` `competition=La Liga`	totalCross: 1.3016 -> 1.3358 totalShots: 0.8822 -> 0.8557 interceptionWon: 0.6562 -> 0.6805 wonTackle: 0.1061 -> 0.1176 onTargetScoringAttempt: 0.2454 -> 0.238
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Lucien Agoumé', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.301, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8249, 'skill_edge': -0.0871, 'height_edge': -0.032, 'attacker_skill': 0.4429, 'defender_skill': 0.6365, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Lucien Agoumé', 'market_value': 18500000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.6365}], 'xg_override': 0.0472}	aerialWon: 0.1727 -> 1.0 totalShots: 0.8748 -> 0.7216 shotOffTarget: 0.6368 -> 0.5253 onTargetScoringAttempt: 0.238 -> 0.1963 goals: 0.0614 -> 0.0506 expectedGoals: 0.0572 -> 0.0472
`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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0472 -> 0.0663 expected_assists: 0.0734 -> 0.1091
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 79.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0641` `goal_rate=0.0506` `scorer_weight=0.0686`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1034` `assist_rate=0.0688` `provider_weight=0.105`	-

Davinchi D 66 0 0.01 0.00 402% 0 0.1 6.7 30.3 23 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 0.9958, quality 0.437)	`market_value_eur=1800000` `quality_factor=0.4374` `boost_factor=0.9958` `reference_quality=0.505` `history_matches=19` `history_shrink=0.2083`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0045)	`blend_weight=0.0045` `history_matches=19` `season_overlap_discount=1.0` `per90_to_match_factor=0.7354` `prior_reliability=0.0333` `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': 'Youssouf Fofana', 'matchup_zone': 'LM 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 1.33 (squad xG sum 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0311 -> 0.0462
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 69.0)	`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=0.0117` `goal_rate=0.0` `scorer_weight=0.0101`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0451` `assist_rate=0.0` `provider_weight=0.037`	-

David Soria G 84 0 0.00 - n/a 0.0 7.0 66.0 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 0.9981, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9981` `reference_quality=0.505` `history_matches=48` `history_shrink=0.0943`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0123)	`blend_weight=0.0123` `history_matches=48` `season_overlap_discount=1.0` `per90_to_match_factor=0.9328` `prior_reliability=0.2` `competition=La Liga`	saves: 2.9971 -> 2.9908 wasFouled: 0.2123 -> 0.2173
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Félix Correia, Lucas Stassin', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2934}`	-
`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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	shots_faced: 12.3 -> 15.8 expected_saves: 3.01 -> 3.87 high_pressure_saves: 1.03 -> 1.33
`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=0.0` `scorer_weight=0.0` `squad_weight_total=1.327`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.9122`	-

Andrés García D 76 0 0.05 0.01 208% 1 0.4 6.7 42.5 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 0.9991, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9991` `reference_quality=0.505` `history_matches=14` `history_shrink=0.2632`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0285)	`blend_weight=0.0285` `history_matches=14` `season_overlap_discount=1.0` `per90_to_match_factor=0.8491` `prior_reliability=0.1667` `competition=La Liga`	wonTackle: 1.1103 -> 1.1367 interceptionWon: 0.7181 -> 0.6976 fouls: 0.6506 -> 0.632 totalShots: 0.5503 -> 0.5632 totalCross: 2.9733 -> 2.9854 wasFouled: 0.1355 -> 0.1413 onTargetScoringAttempt: 0.1875 -> 0.1822
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Isaac Romero', '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 1.33 (squad xG sum 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0325 -> 0.0456 expected_assists: 0.0415 -> 0.0617
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 73.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0446` `goal_rate=0.0` `scorer_weight=0.0365`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0598` `assist_rate=0.0` `provider_weight=0.0494`	-

Dani Carvajal D 77 0 0.03 0.01 212% 0 0.1 6.7 38.5 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 0.9961, quality 0.442)	`market_value_eur=3400000` `quality_factor=0.4424` `boost_factor=0.9961` `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': 'Gabriel Suazo', '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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0216 -> 0.0303 expected_assists: 0.0867 -> 0.1289
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 80.0)	`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=0.0298` `goal_rate=0.0` `scorer_weight=0.0242`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1209` `assist_rate=0.1258` `provider_weight=0.1611`	-

Nemanja Gudelj M 81 0 0.09 0.03 219% 1 0.8 6.7 56.3 42 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=1900000` `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 0.0009)	`blend_weight=0.0009` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9022` `prior_reliability=0.0133` `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': 'Lucien Agoumé', '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 1.33 (squad xG sum 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0671 -> 0.0942 expected_assists: 0.0304 -> 0.0452
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 78.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0899` `goal_rate=0.0591` `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=0.0442` `assist_rate=0.0464` `provider_weight=0.0542`	-

Djené D 75 0 0.00 - n/a 0 0.0 6.6 58.1 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 0.9979, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0131)	`blend_weight=0.0131` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.8328` `prior_reliability=0.1933` `competition=La Liga`	fouls: 0.9704 -> 0.9765
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Lucas Stassin', '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 0.9446, xG scale 1.4038, xA scale 1.4866, team xA 0.86 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.326` `squad_xg_sum=0.9446` `squad_xa_sum=0.5798` `team_expected_assists=0.8619` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 79.0)	`match_squad_rank=17` `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=0.0004` `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=0.014` `assist_rate=0.0` `provider_weight=0.0118`	-

Team totals 1 1.33 12 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Jiří Letáček	G	4.4m	10.9%	Market-value substitute prior
Zaid Romero	D	13.7m	21.9%	Market-value substitute prior
Abdel Abqar	D	6.7m	41.0%	Market-value substitute prior
Mario Martín	M	22.3m	31.4%	Market-value substitute prior
Mauro Arambarri	M	22.2m	51.0%	Market-value substitute prior
Christantus Uche	F	25.8m	58.1%	Market-value substitute prior

Sevilla — 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

Odysseas Vlachodimos G 90 0 0.00 - n/a 0.0 6.9 60.6 34 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9980, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.998` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0135)	`blend_weight=0.0135` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Enes Ünal, Martín Satriano', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.9811}`	-
`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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	shots_faced: 9.3 -> 12.6 expected_saves: 2.27 -> 3.08 high_pressure_saves: 0.78 -> 1.06
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 79.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=1.6973`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=1.029`	-

Juan Iglesias D 88 0 0.07 0.03 110% 1 0.7 6.8 63.6 34 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9990, quality 0.472)	`market_value_eur=5800000` `quality_factor=0.472` `boost_factor=0.999` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Martín Satriano', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.66 (squad xG sum 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0583 -> 0.0717 expected_assists: 0.0915 -> 0.1175
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 76.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0692` `goal_rate=0.0689` `scorer_weight=0.0787`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1109` `assist_rate=0.0049` `provider_weight=0.094`	-

Andrés Castrin D 90 0 0.04 0.02 154% 1 0.3 6.8 45.9 30 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 1.0001, quality 0.507)	`market_value_eur=8700000` `quality_factor=0.5071` `boost_factor=1.0001` `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': 'Enes Ünal', '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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0339 -> 0.0417 expected_assists: 0.0316 -> 0.0406
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 73.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0408` `goal_rate=0.0359` `scorer_weight=0.0427`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0398` `assist_rate=0.0` `provider_weight=0.0325`	-

Kike Salas D 90 0 0.07 0.06 ok 1 0.8 6.8 63.2 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0030, quality 0.584)	`market_value_eur=15400000` `quality_factor=0.5835` `boost_factor=1.003` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0111)	`blend_weight=0.0111` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.9988` `prior_reliability=0.1333` `competition=La Liga`	wasFouled: 0.548 -> 0.5586 totalShots: 0.8999 -> 0.9069 onTargetScoringAttempt: 0.5622 -> 0.556
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Enes Ünal', '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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0587 -> 0.0722 expected_assists: 0.0412 -> 0.0529
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0697` `goal_rate=0.0336` `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=0` `assist_probability=0.0515` `assist_rate=0.0` `provider_weight=0.0423`	-

Gabriel Suazo D 88 0 0.01 0.01 54% 0 0.2 6.8 56.0 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9996, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9996` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0148)	`blend_weight=0.0148` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.9812` `prior_reliability=0.2` `competition=La Liga`	totalCross: 2.1035 -> 2.1256 fouls: 1.576 -> 1.5962
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dani Carvajal', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.66 (squad xG sum 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.1437 -> 0.1844
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 74.0)	`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=0.0098` `goal_rate=0.0` `scorer_weight=0.0084`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1684` `assist_rate=0.0016` `provider_weight=0.1475`	-

Chidera Ejuke F 71 0 0.11 0.04 210% 1 0.6 6.8 49.6 33 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.446)	`market_value_eur=3700000` `quality_factor=0.4461` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0054)	`blend_weight=0.0054` `history_matches=35` `season_overlap_discount=1.0` `per90_to_match_factor=0.7928` `prior_reliability=0.0667` `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': 'Davinchi, Djené', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.188, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9822, 'skill_edge': 0.0039, 'height_edge': -0.016, 'attacker_skill': 0.4461, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Davinchi', 'market_value': 1800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Djené', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.0898}	totalShots: 1.1978 -> 1.1765 shotOffTarget: 0.8232 -> 0.8085 onTargetScoringAttempt: 0.3746 -> 0.3679
`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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0898 -> 0.1104 expected_assists: 0.0813 -> 0.1044
`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=0.1045` `goal_rate=0.1671` `scorer_weight=0.138`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0991` `assist_rate=0.0` `provider_weight=0.0835`	-

Lucien Agoumé M 88 0 0.07 0.02 193% 1 0.5 6.9 62.1 33 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0034, quality 0.616)	`market_value_eur=18500000` `quality_factor=0.6161` `boost_factor=1.0034` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0133)	`blend_weight=0.0133` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9829` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 0.4188 -> 0.435 wonTackle: 2.1139 -> 2.1293 totalCross: 0.1896 -> 0.2045 fouls: 1.7691 -> 1.7804 interceptionWon: 1.3372 -> 1.3455
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Nemanja Gudelj', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.532, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1199, 'skill_edge': 0.0896, 'height_edge': -0.008, 'attacker_skill': 0.6365, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Nemanja Gudelj', 'market_value': 1900000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0535}	aerialWon: 0.4307 -> 1.2 totalShots: 0.6281 -> 0.7034 shotOffTarget: 0.4546 -> 0.5091 onTargetScoringAttempt: 0.1707 -> 0.1912 expectedGoalsOnTarget: 0.069 -> 0.0773 goals: 0.0525 -> 0.0588 expectedGoals: 0.0478 -> 0.0535
`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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0535 -> 0.0658 expected_assists: 0.0463 -> 0.0594
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 76.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0637` `goal_rate=0.0588` `scorer_weight=0.0692`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0577` `assist_rate=0.0515` `provider_weight=0.0626`	-

Youssouf Fofana M 86 0 0.19 0.09 111% 2 1.1 6.9 50.6 10 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0110, quality 0.593)	`market_value_eur=16300000` `quality_factor=0.5932` `boost_factor=1.011` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=true`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Davinchi', 'matchup_zone': 'LM vs CB', 'duel_win_rate': 0.511, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1332, 'skill_edge': 0.0786, 'height_edge': 0.012, 'attacker_skill': 0.6121, 'defender_skill': 0.4374, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Davinchi', 'market_value': 1800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.1511}`	aerialWon: 0.8265 -> 1.2 totalShots: 1.6173 -> 1.8327 shotOffTarget: 1.0258 -> 1.1624 onTargetScoringAttempt: 0.5915 -> 0.6703 bigChanceMissed: 0.2555 -> 0.2895 expectedGoalsOnTarget: 0.229 -> 0.2595 goals: 0.1351 -> 0.1531 expectedGoals: 0.1333 -> 0.1511
`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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1511 -> 0.1857 expected_assists: 0.112 -> 0.1438
`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: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1695` `goal_rate=0.1531` `scorer_weight=0.1875`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1339` `assist_rate=0.1606` `provider_weight=0.1798`	-

Lucas Stassin F 76 1 0.31 0.10 201% 2 1.0 6.8 42.6 8 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 1.0123, quality 0.587)	`market_value_eur=15700000` `quality_factor=0.5868` `boost_factor=1.0123` `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': 'Davinchi, Djené', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.283, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1223, 'skill_edge': 0.0672, 'height_edge': 0.016, 'attacker_skill': 0.5868, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Davinchi', 'market_value': 1800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Djené', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.252}	totalShots: 2.0092 -> 2.2549 shotOffTarget: 1.318 -> 1.4792 onTargetScoringAttempt: 0.6911 -> 0.7756 bigChanceMissed: 0.4652 -> 0.5221 expectedGoals: 0.2245 -> 0.252 goals: 0.2247 -> 0.2522 expectedGoalsOnTarget: 0.1407 -> 0.1579
`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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.252 -> 0.3097 expected_assists: 0.041 -> 0.0526
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 74.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2663` `goal_rate=0.2522` `scorer_weight=0.3099`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0512` `assist_rate=0.0` `provider_weight=0.0421`	-

Isaac Romero F 65 0 0.27 0.09 212% 2 0.9 6.7 51.9 33 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9986, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.9986` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0067)	`blend_weight=0.0067` `history_matches=37` `season_overlap_discount=1.0` `per90_to_match_factor=0.7209` `prior_reliability=0.0867` `competition=La Liga`	fouls: 1.5915 -> 1.5994
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Davinchi, Djené', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.228, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0415, 'skill_edge': 0.0122, 'height_edge': 0.016, 'attacker_skill': 0.4646, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Davinchi', 'market_value': 1800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Djené', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.2172}	totalShots: 1.7879 -> 1.8621 shotOffTarget: 1.1995 -> 1.2493 onTargetScoringAttempt: 0.5884 -> 0.6128 goals: 0.2192 -> 0.2283 expectedGoals: 0.2085 -> 0.2172 bigChanceMissed: 0.1349 -> 0.1405 expectedGoalsOnTarget: 0.1245 -> 0.1297
`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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2172 -> 0.267 expected_assists: 0.0441 -> 0.0566
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 74.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2343` `goal_rate=0.2283` `scorer_weight=0.2781`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.055` `assist_rate=0.0037` `provider_weight=0.0453`	-

Félix Correia F 77 1 0.32 0.14 135% 2 0.8 6.9 43.3 16 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0019, quality 0.519)	`market_value_eur=9700000` `quality_factor=0.5189` `boost_factor=1.0019` `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': 'Davinchi, Djené', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.229, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0422, 'skill_edge': 0.0367, 'height_edge': -0.008, 'attacker_skill': 0.5189, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Davinchi', 'market_value': 1800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Djené', 'market_value': 1500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.2608}	totalShots: 1.9416 -> 2.0236 shotOffTarget: 1.2742 -> 1.328 onTargetScoringAttempt: 0.6674 -> 0.6956 bigChanceMissed: 0.2532 -> 0.2639 expectedGoals: 0.2502 -> 0.2608 goals: 0.2346 -> 0.2445 expectedGoalsOnTarget: 0.224 -> 0.2335
`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 1.3489, xG scale 1.2292, xA scale 1.2838, team xA 1.08 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.658` `squad_xg_sum=1.3489` `squad_xa_sum=0.8394` `team_expected_assists=1.0777` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2608 -> 0.3205 expected_assists: 0.1066 -> 0.1369
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 75.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2742` `goal_rate=0.2445` `scorer_weight=0.3037`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1279` `assist_rate=0.1482` `provider_weight=0.1711`	-

Team totals 2 1.66 16 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Fran González	G	4.4m	10.9%	Market-value substitute prior
José Ángel Carmona	D	14.0m	31.6%	Market-value substitute prior
Arouna Sangante	D	13.8m	22.2%	Market-value substitute prior
Dodi Lukebakio	M	22.5m	52.2%	Market-value substitute prior
Oso	M	22.3m	51.5%	Market-value substitute prior
Akor Adams	F	25.8m	58.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Orel Mangala vs Lucien Agoumé will be the pivotal duel. Total antagonist xG — Home: 0.64, Away: 1.02. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 48.1% / 51.9%, dominance ratio 0.45, key duel: Orel Mangala vs Lucien Agoumé

Dani Carvajal xG 0.02Orel Mangala xG 0.04Francho Serrano xG 0.05Youssouf Fofana xG 0.15Lucien Agoumé xG 0.05Lucas Stassin xG 0.25

Summary

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

Tactical parity between 5-3-2 and 4-4-2. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Orel Mangala vs Lucien Agoumé will be the pivotal duel. Total antagonist xG — Home: 0.64, Away: 1.02. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Elche vs Valencia

LaLiga · 20261101 · 4-2-3-1 vs 4-3-3

Predicted 1-0Winner: ElcheWinning H 1-0 (10.1%)Winning A 0-1 (7.6%)Confidence 0.72λ home/away 1.54 / 1.18Most-likely P 10.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Elche vs Valencia. 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 4-3-3 (duel lambdas: Home 1.154, Away 0.870). Final calibrated Poisson lambdas: Home 1.545, Away 1.176 (most likely score 1-0).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.15 / 0.87 Final λ (H/A) 1.54 / 1.18

FBref Team Priors: Elche (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.244) vs Valencia (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.247) | 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	Elche	Valencia
League position	16.00	19.00
Points per game	1.14	0.89
Attack index	0.97	0.76
Defense (concede) index	1.06	1.06
Form multiplier	1.01	0.98
Standing λ multiplier	1.01	0.91

Lambda decomposition (how the goal rates were built)

Stage	Elche λ	Valencia λ
FBref Squad Prior E[λ] (weight 0.228)	0.244	0.247
Pre-competitive-floor	1.121	0.895
Pre-calibration (Micro-duels)	1.154	0.870
Final λ	1.545	1.176

competition calibration scale 1.35competition 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	12.1%
1-0	10.1%
2-1	9.2%
2-0	7.8%
0-1	7.6%

Home win	45.7%
Draw	25.4%
Away win	28.9%
Over 2.5	51.1%
BTTS yes	54.5%

Pregame fair line — favorite Elche (45.7%), fair total 2.72, fair spread 0.37

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.

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

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

Buba Sangaré D 77 0 0.01 0.01 ok 0 0.1 6.7 51.0 27 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9975, quality 0.461)	`market_value_eur=4900000` `quality_factor=0.4609` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0242)	`blend_weight=0.0242` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.8517` `prior_reliability=0.1933` `competition=La Liga`	wonTackle: 1.0755 -> 1.0921 interceptionWon: 0.712 -> 0.7019 totalCross: 0.9708 -> 0.9615 goals: 0.0602 -> 0.0658 onTargetScoringAttempt: 0.0602 -> 0.0657 fouls: 1.2586 -> 1.2637
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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 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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_assists: 0.014 -> 0.0217
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 69.0)	`match_squad_rank=17` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0057` `goal_rate=0.0657` `scorer_weight=0.0071`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0215` `assist_rate=0.0` `provider_weight=0.0174`	-

Federico Redondo M 71 0 0.09 0.05 84% 1 0.1 6.8 34.6 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 0.9956, quality 0.437)	`market_value_eur=2400000` `quality_factor=0.4374` `boost_factor=0.9956` `reference_quality=0.505` `history_matches=18` `history_shrink=0.2174`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0141)	`blend_weight=0.0141` `history_matches=18` `season_overlap_discount=1.0` `per90_to_match_factor=0.7874` `prior_reliability=0.1` `competition=La Liga`	fouls: 0.9918 -> 0.9852 wasFouled: 0.9072 -> 0.9018
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 0.384, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9762, 'skill_edge': -0.0282, 'height_edge': 0.012, 'attacker_skill': 0.4374, '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': 0.0562}	aerialWon: 0.1147 -> 1.2 totalShots: 0.5412 -> 0.5283 shotOffTarget: 0.3713 -> 0.3625
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.0562 -> 0.087 expected_assists: 0.0319 -> 0.0494
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 70.0)	`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=0.0833` `goal_rate=0.0585` `scorer_weight=0.0889`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0482` `assist_rate=0.0552` `provider_weight=0.0617`	-

Víctor Chust D 90 0 0.05 0.02 141% 1 0.3 6.9 62.1 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9978` `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=0.9958` `prior_reliability=0.2` `competition=La Liga`	totalCross: 0.9215 -> 0.9366
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Luis Rioja', '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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.0326 -> 0.0505 expected_assists: 0.0306 -> 0.0474
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 74.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0492` `goal_rate=0.033` `scorer_weight=0.0507`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0463` `assist_rate=0.056` `provider_weight=0.0592`	-

Roy Revivo D 89 0 0.03 0.02 44% 1 0.3 6.8 48.3 10 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 0.9940, quality 0.457)	`market_value_eur=4600000` `quality_factor=0.4572` `boost_factor=0.994` `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': '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 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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.0199 -> 0.0308 expected_assists: 0.1244 -> 0.1926
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 80.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_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=0.0303` `goal_rate=0.0` `scorer_weight=0.0246`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1752` `assist_rate=0.294` `provider_weight=0.2407`	-

Gonzalo Villar M 76 0 0.11 0.03 351% 1 0.4 6.9 52.3 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 0.9962, quality 0.437)	`market_value_eur=1700000` `quality_factor=0.4374` `boost_factor=0.9962` `reference_quality=0.505` `history_matches=22` `history_shrink=0.1852`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0241)	`blend_weight=0.0241` `history_matches=22` `season_overlap_discount=1.0` `per90_to_match_factor=0.8427` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 1.93 -> 1.9782 totalCross: 1.0878 -> 1.1225 fouls: 1.3978 -> 1.4182 onTargetScoringAttempt: 0.2613 -> 0.2753 totalShots: 0.8491 -> 0.8556
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Guido Rodríguez', 'matchup_zone': 'Attacking Mid vs Single Holding Mid — Space Creator Duel', 'duel_win_rate': 0.437, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9663, 'skill_edge': -0.0069, 'height_edge': -0.016, 'attacker_skill': 0.4374, 'defender_skill': 0.4527, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Guido Rodríguez', 'market_value': 3600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4527}], 'xg_override': 0.0737}	aerialWon: 0.6516 -> 1.1 totalShots: 0.8631 -> 0.834 shotOffTarget: 0.5878 -> 0.568 onTargetScoringAttempt: 0.2753 -> 0.266
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.0737 -> 0.1141 expected_assists: 0.0909 -> 0.1407
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 72.0)	`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=0.1078` `goal_rate=0.067` `scorer_weight=0.1079`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1313` `assist_rate=0.102` `provider_weight=0.1518`	-

Javi Morcillo M 87 0 0.06 0.02 240% 1 0.2 6.7 41.8 21 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9944, quality 0.437)	`market_value_eur=2100000` `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 0.0048)	`blend_weight=0.0048` `history_matches=13` `season_overlap_discount=1.0` `per90_to_match_factor=0.9707` `prior_reliability=0.0267` `competition=La Liga`	fouls: 0.725 -> 0.7332 wonTackle: 1.1344 -> 1.1406 interceptionWon: 1.0719 -> 1.0667
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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': 0.364, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9468, 'skill_edge': -0.0282, 'height_edge': -0.008, 'attacker_skill': 0.4374, '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': 0.0373}	aerialWon: 0.6603 -> 1.1 totalShots: 0.5542 -> 0.5247 shotOffTarget: 0.424 -> 0.4014 onTargetScoringAttempt: 0.1302 -> 0.1233
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.0373 -> 0.0578 expected_assists: 0.0258 -> 0.0399
`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_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=0.0562` `goal_rate=0.0503` `scorer_weight=0.0664`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0391` `assist_rate=0.044` `provider_weight=0.0495`	-

Lucas Cepeda F 76 0 0.16 0.05 236% 2 0.8 6.9 42.6 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9959, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9959` `reference_quality=0.505` `history_matches=20` `history_shrink=0.2`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0078)	`blend_weight=0.0078` `history_matches=20` `season_overlap_discount=1.0` `per90_to_match_factor=0.8458` `prior_reliability=0.06` `competition=La Liga`	totalCross: 1.8527 -> 1.8822 totalShots: 1.6818 -> 1.7058 fouls: 0.6266 -> 0.6437 onTargetScoringAttempt: 0.7042 -> 0.7136 wasFouled: 2.0331 -> 2.0246 wonTackle: 1.0198 -> 1.0118 interceptionWon: 0.916 -> 0.9235 goalAssist: 0.0 -> 0.0073
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Arnau Martínez, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8592, 'skill_edge': -0.0558, 'height_edge': -0.04, 'attacker_skill': 0.4374, 'defender_skill': 0.5614, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Arnau Martínez', 'market_value': 10800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5726}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.1005}	totalShots: 1.7058 -> 1.4656 shotOffTarget: 0.9776 -> 0.84 onTargetScoringAttempt: 0.7136 -> 0.6131 goals: 0.1538 -> 0.1321 expectedGoals: 0.117 -> 0.1005 expectedGoalsOnTarget: 0.0459 -> 0.0394
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.1005 -> 0.1556 expected_assists: 0.1085 -> 0.168
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 71.0)	`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=0.1441` `goal_rate=0.1321` `scorer_weight=0.1883`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1546` `assist_rate=0.0073` `provider_weight=0.1344`	-

Thomas Lemar M 72 0 0.10 0.06 60% 1 0.6 7.1 60.3 30 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9974, quality 0.437)	`market_value_eur=1900000` `quality_factor=0.4374` `boost_factor=0.9974` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pablo Maffeo', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.466, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9788, 'skill_edge': -0.0024, 'height_edge': -0.012, 'attacker_skill': 0.4374, 'defender_skill': 0.4428, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Pablo Maffeo', 'market_value': 2400000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4428}], 'xg_override': 0.0655}	aerialWon: 0.0199 -> 0.8 totalShots: 0.9443 -> 0.9243 shotOffTarget: 0.6415 -> 0.6279 onTargetScoringAttempt: 0.3028 -> 0.2964
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.0655 -> 0.1014 expected_assists: 0.1163 -> 0.1801
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 77.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0964` `goal_rate=0.0813` `scorer_weight=0.1153`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1648` `assist_rate=0.0981` `provider_weight=0.1604`	-

Germán Valera F 86 0 0.19 0.05 318% 1 0.5 7.0 58.5 42 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9992, quality 0.477)	`market_value_eur=6200000` `quality_factor=0.4769` `boost_factor=0.9992` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Arnau Martínez, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8559, 'skill_edge': -0.038, 'height_edge': -0.06, 'attacker_skill': 0.4769, 'defender_skill': 0.5614, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Arnau Martínez', 'market_value': 10800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5726}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.123}	totalShots: 1.1989 -> 1.0261 shotOffTarget: 0.7187 -> 0.6151 onTargetScoringAttempt: 0.4801 -> 0.4109 goals: 0.2152 -> 0.1842 expectedGoals: 0.1437 -> 0.123 expectedGoalsOnTarget: 0.0807 -> 0.0691 bigChanceMissed: 0.0569 -> 0.0487
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.123 -> 0.1905 expected_assists: 0.1162 -> 0.1799
`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=0` `goal_probability=0.1735` `goal_rate=0.1842` `scorer_weight=0.2381`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1646` `assist_rate=0.0349` `provider_weight=0.1439`	-

Fernando Niño F 73 1 0.54 0.32 73% 2 1.2 6.8 54.1 13 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9940, quality 0.445)	`market_value_eur=3600000` `quality_factor=0.4449` `boost_factor=0.994` `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=0.8061` `prior_reliability=0.1667` `competition=La Liga`	totalShots: 2.1609 -> 2.1291 fouls: 1.0612 -> 1.0345 totalOffside: 0.3119 -> 0.3006 wasFouled: 1.354 -> 1.3633 wonTackle: 0.8152 -> 0.8207 interceptionWon: 0.1843 -> 0.1893
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Arnau Martínez, César Tárrega', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9406, 'skill_edge': -0.0524, 'height_edge': 0.012, 'attacker_skill': 0.4449, 'defender_skill': 0.5614, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Arnau Martínez', 'market_value': 10800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5726}, {'player': 'César Tárrega', 'market_value': 9300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5502}], 'xg_override': 0.3517}	totalShots: 2.1576 -> 2.0294 shotOffTarget: 1.1103 -> 1.0443 onTargetScoringAttempt: 1.0473 -> 0.9851 expectedGoalsOnTarget: 0.6831 -> 0.6425 goals: 0.4092 -> 0.3849 expectedGoals: 0.3739 -> 0.3517 bigChanceMissed: 0.1567 -> 0.1474
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	expected_goals: 0.3517 -> 0.5446 expected_assists: 0.0385 -> 0.0596
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 81.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.4199` `goal_rate=0.3849` `scorer_weight=0.5896`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0579` `assist_rate=0.0` `provider_weight=0.0477`	-

Matías Dituro G 90 0 0.00 - n/a 0.0 7.3 54.9 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 0.9973, quality 0.437)	`market_value_eur=105000` `quality_factor=0.4374` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0176)	`blend_weight=0.0176` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.9148 -> 2.9046
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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, Arnaut Danjuma', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.8704}`	-
`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 1.54 (squad xG sum 0.9978, xG scale 1.5484, xA scale 1.5484, team xA 1.15 = 0.74 x lambda)	`scoreline_reset=true` `team_lambda=1.545` `squad_xg_sum=0.9978` `squad_xa_sum=0.7401` `team_expected_assists=1.1459` `team_xa_to_xg_ratio=0.7417`	shots_faced: 8.3 -> 11.2 expected_saves: 2.03 -> 2.74 high_pressure_saves: 0.7 -> 0.94
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 76.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.72`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=1.141`	-

Team totals 1 1.54 14 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

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

Valencia — 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

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': 'Fernando Niño, Germán Valera', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.1544}`	-
`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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	shots_faced: 11.0 -> 14.7 expected_saves: 2.7 -> 3.6 high_pressure_saves: 0.92 -> 1.24
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 77.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3468`	-
`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=0.9711`	-

Arnau Martínez D 79 0 0.08 0.04 125% 0 0.5 6.8 56.3 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0009, quality 0.532)	`market_value_eur=10800000` `quality_factor=0.5318` `boost_factor=1.0009` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0042)	`blend_weight=0.0042` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.8783` `prior_reliability=0.06` `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': 'Fernando Niño', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.0616 -> 0.0836 expected_assists: 0.0472 -> 0.064
`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=0.0802` `goal_rate=0.0955` `scorer_weight=0.1045`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.062` `assist_rate=0.0972` `provider_weight=0.08`	-

César Tárrega D 83 0 0.06 0.02 162% 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': 'Fernando Niño', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.0425 -> 0.0576
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 75.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.056` `goal_rate=0.0` `scorer_weight=0.0461`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0079` `assist_rate=0.0` `provider_weight=0.0071`	-

Pepelu M 85 0 0.07 0.10 ok 1 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 Redondo', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.466, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0238, 'skill_edge': 0.0282, 'height_edge': -0.012, 'attacker_skill': 0.5, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Federico Redondo', 'market_value': 2400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0545}	aerialWon: 0.5012 -> 1.2 totalShots: 0.5882 -> 0.6022 shotOffTarget: 0.4094 -> 0.4191
`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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.0545 -> 0.0739 expected_assists: 0.0391 -> 0.053
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 76.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0712` `goal_rate=0.0657` `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=0.0516` `assist_rate=0.0516` `provider_weight=0.0604`	-

José Luis Gayà D 83 0 0.06 0.03 116% 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': 'Lucas Cepeda', '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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.0453 -> 0.0614 expected_assists: 0.0598 -> 0.0811
`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=0.0596` `goal_rate=0.0052` `scorer_weight=0.0491`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0779` `assist_rate=0.0313` `provider_weight=0.0649`	-

Aaron Mayol M 88 0 0.08 0.01 1278% 1 0.1 6.9 9.4 15 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9900, quality 0.458)	`market_value_eur=4700000` `quality_factor=0.4585` `boost_factor=0.99` `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': 'Federico Redondo', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.442, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9888, 'skill_edge': 0.0124, 'height_edge': -0.02, 'attacker_skill': 0.4649, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Federico Redondo', 'market_value': 2400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0599}	aerialWon: 0.0 -> 1.1 totalShots: 0.8466 -> 0.8371 shotOffTarget: 0.5919 -> 0.5853
`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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.0599 -> 0.0813 expected_assists: 0.0795 -> 0.1078
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0781` `goal_rate=0.1137` `scorer_weight=0.1016`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1022` `assist_rate=0.1033` `provider_weight=0.1276`	-

Guido Rodríguez M 86 0 0.06 0.04 51% 1 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 Redondo', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.415, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9925, 'skill_edge': 0.0069, 'height_edge': -0.012, 'attacker_skill': 0.4527, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Federico Redondo', 'market_value': 2400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0412}	aerialWon: 1.2549 -> 1.2
`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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.0412 -> 0.0559 expected_assists: 0.0355 -> 0.0482
`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=0.0544` `goal_rate=0.0557` `scorer_weight=0.0648`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0471` `assist_rate=0.0471` `provider_weight=0.0547`	-

Javier Guerra M 81 0 0.24 0.10 133% 2 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': 'Federico Redondo', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.568, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1739, 'skill_edge': 0.1223, 'height_edge': -0.004, 'attacker_skill': 0.7091, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Federico Redondo', 'market_value': 2400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.1769}	aerialWon: 0.618 -> 1.2 totalShots: 1.6694 -> 1.9597 shotOffTarget: 1.1408 -> 1.3392 onTargetScoringAttempt: 0.5286 -> 0.6205 bigChanceMissed: 0.2735 -> 0.3211 goals: 0.1959 -> 0.23 expectedGoals: 0.1507 -> 0.1769 expectedGoalsOnTarget: 0.1226 -> 0.1439
`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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.1769 -> 0.24 expected_assists: 0.126 -> 0.171
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 82.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.2134` `goal_rate=0.23` `scorer_weight=0.2962`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1572` `assist_rate=0.1375` `provider_weight=0.1822`	-

Pablo Maffeo D 82 0 0.02 0.01 88% 0 0.3 6.7 59.3 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=2400000` `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 0.0038)	`blend_weight=0.0038` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9154` `prior_reliability=0.0533` `competition=La Liga`	totalCross: 2.7296 -> 2.7411
`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': 'Thomas Lemar', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.0169 -> 0.0229 expected_assists: 0.0557 -> 0.0756
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 82.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0226` `goal_rate=0.001` `scorer_weight=0.0183`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0728` `assist_rate=0.0634` `provider_weight=0.0811`	-

Arnaut Danjuma F 83 0 0.19 0.08 133% 2 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': 'Buba Sangaré, Roy Revivo', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9405, 'skill_edge': -0.0185, 'height_edge': -0.022, 'attacker_skill': 0.4374, 'defender_skill': 0.4785, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Buba Sangaré', 'market_value': 4900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4809}, {'player': 'Roy Revivo', 'market_value': 4600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4761}], 'xg_override': 0.1365}	totalShots: 1.5943 -> 1.4994 shotOffTarget: 0.9717 -> 0.9139 onTargetScoringAttempt: 0.6088 -> 0.5726 bigChanceMissed: 0.4115 -> 0.387 goals: 0.1932 -> 0.1817 expectedGoals: 0.1451 -> 0.1365 expectedGoalsOnTarget: 0.107 -> 0.1006
`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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.1365 -> 0.1852 expected_assists: 0.0938 -> 0.1272
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 75.0)	`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=0.1691` `goal_rate=0.1817` `scorer_weight=0.2301`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1194` `assist_rate=0.032` `provider_weight=0.1018`	-

Luis Rioja F 79 0 0.14 0.05 210% 1 0.7 6.8 58.1 34 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 0.9979, quality 0.437)	`market_value_eur=1900000` `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': 'Matías Dituro', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.36, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9118, 'skill_edge': 0.0, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Matías Dituro', 'market_value': 105000, 'role': 'GK', 'price_index': 0.55, 'adjusted_quality': 0.4374}], 'xg_override': 0.1042}	totalShots: 1.0546 -> 0.9616 shotOffTarget: 0.7231 -> 0.6593 onTargetScoringAttempt: 0.3315 -> 0.3023 goals: 0.1426 -> 0.13 expectedGoals: 0.1143 -> 0.1042 bigChanceMissed: 0.0839 -> 0.0765 expectedGoalsOnTarget: 0.0747 -> 0.0681
`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 1.18 (squad xG sum 0.8670, xG scale 1.3565, xA scale 1.3565, team xA 0.93 = 0.79 x lambda)	`scoreline_reset=true` `team_lambda=1.176` `squad_xg_sum=0.867` `squad_xa_sum=0.6851` `team_expected_assists=0.9294` `team_xa_to_xg_ratio=0.7903`	expected_goals: 0.1042 -> 0.1413 expected_assists: 0.0917 -> 0.1244
`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=0.1318` `goal_rate=0.13` `scorer_weight=0.1649`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.117` `assist_rate=0.1164` `provider_weight=0.1461`	-

Team totals 0 1.18 13 6.9

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
Justin De Haas	D	13.8m	22.2%	Market-value substitute prior
José Copete	D	13.7m	30.2%	Market-value substitute prior
Harvey Elliott	M	22.8m	53.5%	Market-value substitute prior
Filip Ugrinić	M	29.8m	43.8%	Market-value substitute prior
Hugo Duro	F	22.6m	59.9%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Federico Redondo vs Javier Guerra will be the pivotal duel. Total antagonist xG — Home: 0.81, Away: 0.57. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Central Mid vs Defensive Mid — Pressing/Creation Duel.

Midfield — possession 48.5% / 51.5%, dominance ratio 0.46, key duel: Federico Redondo vs Javier Guerra

Thomas Lemar xG 0.07Gonzalo Villar xG 0.07Fernando Niño xG 0.35Luis Rioja xG 0.10Arnaut Danjuma xG 0.14Guido Rodríguez xG 0.04

Summary

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

Tactical parity between 4-2-3-1 and 4-3-3. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Federico Redondo vs Javier Guerra will be the pivotal duel. Total antagonist xG — Home: 0.81, Away: 0.57. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Central Mid vs Defensive Mid — Pressing/Creation Duel.

Generated 2026-11-01 14:36:49 UTC · Soccer prediction reporting