Soccer predictions: actual data vs predicted data

Slate 20261030 · 1 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
Villarreal vs Espanyol LaLiga	2-1	Villarreal	52.7% / 22.9% / 24.4%	58.6%	58.7%	0.74	1.85 / 1.19	-	pending

Match detail

Villarreal vs Espanyol

LaLiga · 20261030 · 4-4-2 vs 4-2-3-1

Predicted 2-1Winner: VillarrealWinning H 2-1 (9.7%)Winning A 1-2 (6.3%)Confidence 0.74λ home/away 1.85 / 1.19Most-likely P 9.7%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Villarreal vs Espanyol. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-4-2 vs 4-2-3-1 (duel lambdas: Home 2.046, Away 1.214). Final calibrated Poisson lambdas: Home 1.848, Away 1.191 (most likely score 2-1).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (7 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 2.05 / 1.21 Final λ (H/A) 1.85 / 1.19

FBref Team Priors: Villarreal (Gls/90: 1.3333333333333333, GA/90: 1.33 → E[λ]: 1.649) vs Espanyol (Gls/90: 1.6666666666666667, GA/90: 1.67 → E[λ]: 1.642) | 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	Villarreal	Espanyol
League position	10.00	18.00
Points per game	1.26	1.01
Attack index	1.00	0.91
Defense (concede) index	0.97	0.97
Form multiplier	1.01	0.98
Standing λ multiplier	0.99	0.95

Lambda decomposition (how the goal rates were built)

Stage	Villarreal λ	Espanyol λ
FBref Squad Prior E[λ] (weight 0.228)	1.649	1.642
Pre-competitive-floor	2.191	1.384
Pre-calibration (Micro-duels)	2.046	1.214
Final λ	1.848	1.191

competition calibration scale 0.85competition 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	10.6%
2-1	9.7%
1-0	8.8%
2-0	8.2%
1-2	6.3%

Home win	52.7%
Draw	22.9%
Away win	24.4%
Over 2.5	58.6%
BTTS yes	58.7%

Pregame fair line — favorite Villarreal (52.7%), fair total 3.04, fair spread 0.66

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.

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

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

Georges Mikautadze F 84 1 0.53 0.39 35% 3 2.0 7.0 63.8 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 1.0093, quality 0.796)	`market_value_eur=43000000` `quality_factor=0.7957` `boost_factor=1.0093` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0129)	`blend_weight=0.0129` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9298` `prior_reliability=0.1867` `competition=La Liga`	totalShots: 2.4169 -> 2.429
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Leandro Cabrera, Vanja Drkušić', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.301, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1488, 'skill_edge': 0.1492, 'height_edge': -0.048, 'attacker_skill': 0.7957, 'defender_skill': 0.464, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Vanja Drkušić', 'market_value': 5500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4907}], 'xg_override': 0.422}	totalShots: 2.429 -> 2.7904 shotOffTarget: 1.269 -> 1.4578 onTargetScoringAttempt: 1.1505 -> 1.3217 expectedGoalsOnTarget: 0.5934 -> 0.6817 bigChanceMissed: 0.5785 -> 0.6646 goals: 0.3763 -> 0.4323 expectedGoals: 0.3673 -> 0.422
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.422 -> 0.5317 expected_assists: 0.093 -> 0.1172
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 79.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.4124` `goal_rate=0.4323` `scorer_weight=0.5433`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1106` `assist_rate=0.2227` `provider_weight=0.1465`	-

Gerard Moreno F 77 0 0.31 0.22 39% 2 1.3 7.0 57.7 29 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9972, quality 0.437)	`market_value_eur=2400000` `quality_factor=0.4374` `boost_factor=0.9972` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=0.8608` `prior_reliability=0.1` `competition=La Liga`	fouls: 0.5412 -> 0.5519 wasFouled: 0.7727 -> 0.7657
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Leandro Cabrera, Vanja Drkušić', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9354, 'skill_edge': -0.012, 'height_edge': -0.032, 'attacker_skill': 0.4374, 'defender_skill': 0.464, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Vanja Drkušić', 'market_value': 5500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4907}], 'xg_override': 0.2484}	totalShots: 1.8756 -> 1.7545 shotOffTarget: 1.2004 -> 1.1229 onTargetScoringAttempt: 0.6752 -> 0.6316 expectedGoalsOnTarget: 0.3383 -> 0.3164 expectedGoals: 0.2656 -> 0.2484 goals: 0.2587 -> 0.242 bigChanceMissed: 0.2216 -> 0.2073
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.2484 -> 0.313 expected_assists: 0.1057 -> 0.1332
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 81.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2688` `goal_rate=0.242` `scorer_weight=0.3063`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1247` `assist_rate=0.0` `provider_weight=0.1066`	-

Alberto Moleiro F 80 1 0.41 0.16 152% 3 1.1 7.4 61.4 42 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0096, quality 0.837)	`market_value_eur=54000000` `quality_factor=0.837` `boost_factor=1.0096` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0067)	`blend_weight=0.0067` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=0.8926` `prior_reliability=0.1067` `competition=La Liga`	totalShots: 2.7059 -> 2.6879 onTargetScoringAttempt: 1.2602 -> 1.2518 wonTackle: 0.6332 -> 0.6401 totalCross: 3.5651 -> 3.5599
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Leandro Cabrera, Vanja Drkušić', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.308, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1585, 'skill_edge': 0.1678, 'height_edge': -0.06, 'attacker_skill': 0.837, 'defender_skill': 0.464, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Leandro Cabrera', 'market_value': 930000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Vanja Drkušić', 'market_value': 5500000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4907}], 'xg_override': 0.3257}	totalShots: 2.6974 -> 3.1249 shotOffTarget: 1.4456 -> 1.6747 onTargetScoringAttempt: 1.2518 -> 1.4502 bigChanceMissed: 0.5902 -> 0.6837 goals: 0.4049 -> 0.4691 expectedGoalsOnTarget: 0.3774 -> 0.4372 expectedGoals: 0.2811 -> 0.3257
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.3257 -> 0.4104 expected_assists: 0.1904 -> 0.24
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 79.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3366` `goal_rate=0.4691` `scorer_weight=0.513`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.2134` `assist_rate=0.328` `provider_weight=0.3`	-

Santi Comesaña M 70 0 0.08 0.07 ok 1 0.4 6.9 62.9 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 1.0000, quality 0.503)	`market_value_eur=8400000` `quality_factor=0.5035` `boost_factor=1.0` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0099)	`blend_weight=0.0099` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.779` `prior_reliability=0.1467` `competition=La Liga`	fouls: 1.4729 -> 1.4794 wonTackle: 0.7787 -> 0.785 totalShots: 0.5823 -> 0.5765 wasFouled: 0.8838 -> 0.8785
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Álex Calatrava', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.517, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.099, 'skill_edge': 0.0194, 'height_edge': 0.048, 'attacker_skill': 0.5146, 'defender_skill': 0.4716, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Álex Calatrava', 'market_value': 4900000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4716}], 'xg_override': 0.0642}	aerialWon: 0.2212 -> 1.2 totalShots: 0.5808 -> 0.6383 shotOffTarget: 0.4297 -> 0.4722 onTargetScoringAttempt: 0.1511 -> 0.1661 bigChanceMissed: 0.1353 -> 0.1487 expectedGoalsOnTarget: 0.0872 -> 0.0958 expectedGoals: 0.0584 -> 0.0642
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.0642 -> 0.0809 expected_assists: 0.0639 -> 0.0805
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 79.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0777` `goal_rate=0.0549` `scorer_weight=0.0743`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0773` `assist_rate=0.0727` `provider_weight=0.0867`	-

Carlos Maciá M 82 0 0.06 0.01 1156% 1 0.1 6.8 30.3 18 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0064, quality 0.574)	`market_value_eur=14500000` `quality_factor=0.5737` `boost_factor=1.0064` `reference_quality=0.505` `history_matches=11` `history_shrink=0.3125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0068)	`blend_weight=0.0068` `history_matches=11` `season_overlap_discount=1.0` `per90_to_match_factor=0.9166` `prior_reliability=0.0333` `competition=La Liga`	wonTackle: 1.0805 -> 1.1104 interceptionWon: 0.7584 -> 0.7657 fouls: 0.7869 -> 0.794
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Álex Calatrava', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.564, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.1673, 'skill_edge': 0.0538, 'height_edge': 0.06, 'attacker_skill': 0.5912, 'defender_skill': 0.4716, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Álex Calatrava', 'market_value': 4900000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4716}], 'xg_override': 0.0507}	aerialWon: 0.3626 -> 1.4 totalShots: 0.5746 -> 0.6708 shotOffTarget: 0.4289 -> 0.5007 onTargetScoringAttempt: 0.1457 -> 0.1701 goals: 0.0541 -> 0.0632 expectedGoals: 0.0434 -> 0.0507
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.0507 -> 0.0639 expected_assists: 0.0405 -> 0.051
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 65.0)	`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=0.0619` `goal_rate=0.0632` `scorer_weight=0.0718`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0497` `assist_rate=0.0497` `provider_weight=0.0562`	-

Tajon Buchanan M 72 0 0.18 0.08 115% 2 1.0 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 1.0017, quality 0.557)	`market_value_eur=13000000` `quality_factor=0.557` `boost_factor=1.0017` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0065)	`blend_weight=0.0065` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.8052` `prior_reliability=0.0933` `competition=La Liga`	totalCross: 3.0137 -> 3.0277 wasFouled: 1.8946 -> 1.9046
`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': 'Omar El Hilali', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel', 'duel_win_rate': 0.422, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9446, 'skill_edge': -0.0377, 'height_edge': 0.0, 'attacker_skill': 0.5731, 'defender_skill': 0.6569, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Omar El Hilali', 'market_value': 15900000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.6569}], 'xg_override': 0.1438}	aerialWon: 0.4572 -> 1.1 totalShots: 1.7996 -> 1.6999 shotOffTarget: 1.1419 -> 1.0786 onTargetScoringAttempt: 0.6577 -> 0.6213 goals: 0.1555 -> 0.1469 expectedGoals: 0.1522 -> 0.1438 bigChanceMissed: 0.1482 -> 0.14 expectedGoalsOnTarget: 0.0984 -> 0.0929
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.1438 -> 0.1812 expected_assists: 0.1516 -> 0.191
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 76.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1657` `goal_rate=0.1469` `scorer_weight=0.1841`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1739` `assist_rate=0.1213` `provider_weight=0.1623`	-

Sergi Cardona D 86 0 0.03 0.01 162% 1 0.4 6.8 47.8 34 FBref Prior D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0000, quality 0.506)	`market_value_eur=8600000` `quality_factor=0.5059` `boost_factor=1.0` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández', '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 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.0256 -> 0.0323 expected_assists: 0.1243 -> 0.1566
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 79.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.0318` `goal_rate=0.0491` `scorer_weight=0.0404`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.145` `assist_rate=0.0095` `provider_weight=0.1253`	-

Renato Veiga D 90 0 0.02 0.01 111% 1 0.2 7.0 57.6 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 1.0067, quality 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.0067` `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=0.9987` `prior_reliability=0.2` `competition=La Liga`	wonTackle: 0.5659 -> 0.5579
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_assists: 0.0779 -> 0.0982
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 78.0)	`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=0.0197` `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=0.0935` `assist_rate=0.0779` `provider_weight=0.0982`	-

Juan Foyth D 78 0 0.04 0.02 70% 1 0.3 7.0 53.9 13 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0001, quality 0.506)	`market_value_eur=8600000` `quality_factor=0.5059` `boost_factor=1.0001` `reference_quality=0.505` `history_matches=19` `history_shrink=0.2083`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0271)	`blend_weight=0.0271` `history_matches=19` `season_overlap_discount=1.0` `per90_to_match_factor=0.8703` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.1314 -> 1.1558 totalShots: 0.5094 -> 0.527 wonTackle: 0.828 -> 0.8449 fouls: 0.6301 -> 0.6209 onTargetScoringAttempt: 0.0973 -> 0.1024 wasFouled: 0.3964 -> 0.4014
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Edu Expósito', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.0334 -> 0.0421 expected_assists: 0.0391 -> 0.0493
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 79.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 2 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=2` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0412` `goal_rate=0.0` `scorer_weight=0.0337`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0481` `assist_rate=0.0` `provider_weight=0.0394`	-

Péter Gulácsi G 90 0 0.00 - n/a 0.0 7.0 36.8 12 FBref Prior G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9908, quality 0.437)	`market_value_eur=970000` `quality_factor=0.4374` `boost_factor=0.9908` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández, Álex Calatrava', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2142}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	shots_faced: 11.5 -> 11.3 expected_saves: 2.81 -> 2.76 high_pressure_saves: 0.97 -> 0.95
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 82.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=1.9647`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by 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=1.3182`	-

Alexander Freeman D 90 0 0.05 0.01 406% 1 0.2 7.1 39.7 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 1.0040, quality 0.566)	`market_value_eur=13800000` `quality_factor=0.566` `boost_factor=1.004` `reference_quality=0.505` `history_matches=18` `history_shrink=0.2174`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roberto Fernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 2 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=2`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.85 (squad xG sum 1.4665, xG scale 1.2601, xA scale 1.2601, team xA 1.31 = 0.71 x lambda)	`scoreline_reset=true` `team_lambda=1.848` `squad_xg_sum=1.4665` `squad_xa_sum=1.0421` `team_expected_assists=1.3132` `team_xa_to_xg_ratio=0.7106`	expected_goals: 0.043 -> 0.0542 expected_assists: 0.0735 -> 0.0926
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 81.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_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=0.0528` `goal_rate=0.235` `scorer_weight=0.0678`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0884` `assist_rate=0.0` `provider_weight=0.0741`	-

Team totals 2 1.85 18 7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Luiz Júnior	G	4.8m	12.9%	Market-value substitute prior
Carlos Romero	D	14.5m	23.6%	Market-value substitute prior
Santiago Mouriño	D	14.3m	23.2%	Market-value substitute prior
Pape Gueye	M	23.3m	33.4%	Market-value substitute prior
Nathan-Dylan Saliba	M	22.5m	52.2%	Market-value substitute prior
Ilias Akhomach	F	20.4m	72.7%	Market-value substitute prior

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

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

Roberto Fernández F 84 1 0.41 0.27 55% 2 1.5 6.8 62.9 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 1.0038, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0038` `reference_quality=0.505` `history_matches=48` `history_shrink=0.0943`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0119)	`blend_weight=0.0119` `history_matches=48` `season_overlap_discount=1.0` `per90_to_match_factor=0.9359` `prior_reliability=0.1933` `competition=La Liga`	totalOffside: 1.167 -> 1.1532 fouls: 1.9089 -> 1.8977 goals: 0.4192 -> 0.4257
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Renato Veiga, Alexander Freeman', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.9469, 'skill_edge': -0.0241, 'height_edge': -0.012, 'attacker_skill': 0.6408, 'defender_skill': 0.6943, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Renato Veiga', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Alexander Freeman', 'market_value': 13800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.615}], 'xg_override': 0.3496}	totalShots: 2.2881 -> 2.1666 shotOffTarget: 1.3568 -> 1.2848 onTargetScoringAttempt: 0.9313 -> 0.8818 goals: 0.4257 -> 0.4031 bigChanceMissed: 0.4033 -> 0.3819 expectedGoals: 0.3692 -> 0.3496 expectedGoalsOnTarget: 0.3351 -> 0.3173
`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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.3496 -> 0.4135
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 74.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3387` `goal_rate=0.4031` `scorer_weight=0.4689`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0413` `assist_rate=0.0219` `provider_weight=0.0343`	-

Bryan Zaragoza F 77 0 0.11 0.12 ok 1 1.2 7.0 61.4 14 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9994, quality 0.493)	`market_value_eur=7500000` `quality_factor=0.4927` `boost_factor=0.9994` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Renato Veiga, Alexander Freeman', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v2', 'xg_multiplier': 0.7784, 'skill_edge': -0.0907, 'height_edge': -0.06, 'attacker_skill': 0.4927, 'defender_skill': 0.6943, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Renato Veiga', 'market_value': 29000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7736}, {'player': 'Alexander Freeman', 'market_value': 13800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.615}], 'xg_override': 0.0895}	totalShots: 1.4191 -> 1.1046 shotOffTarget: 0.9186 -> 0.715 onTargetScoringAttempt: 0.5005 -> 0.3896 expectedGoalsOnTarget: 0.1725 -> 0.1343 goals: 0.1572 -> 0.1224 expectedGoals: 0.115 -> 0.0895
`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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0895 -> 0.1058 expected_assists: 0.1275 -> 0.1401
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 77.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1004` `goal_rate=0.1224` `scorer_weight=0.1307`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1307` `assist_rate=0.0371` `provider_weight=0.1121`	-

Javier Hernández M 77 0 0.12 0.07 72% 1 1.0 6.7 55.7 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 0.9974, quality 0.479)	`market_value_eur=6400000` `quality_factor=0.4793` `boost_factor=0.9974` `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=0.8587` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.0106 -> 1.9504 wasFouled: 1.0497 -> 1.0986 fouls: 1.7738 -> 1.809 goalAssist: 0.2779 -> 0.3051 interceptionWon: 0.5857 -> 0.5645 totalShots: 1.3759 -> 1.3637
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Santi Comesaña', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.358, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9088, 'skill_edge': -0.014, 'height_edge': -0.048, 'attacker_skill': 0.4834, 'defender_skill': 0.5146, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Santi Comesaña', 'market_value': 8400000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5146}], 'xg_override': 0.1025}	aerialWon: 0.1345 -> 0.9 totalShots: 1.3712 -> 1.2461 shotOffTarget: 0.9013 -> 0.8191 onTargetScoringAttempt: 0.4699 -> 0.427 goals: 0.1141 -> 0.1037 expectedGoals: 0.1128 -> 0.1025 expectedGoalsOnTarget: 0.0854 -> 0.0776
`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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1025 -> 0.1212 expected_assists: 0.1383 -> 0.152
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 86.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1141` `goal_rate=0.1037` `scorer_weight=0.1222`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.141` `assist_rate=0.3051` `provider_weight=0.19`	-

Álex Calatrava M 76 0 0.13 0.09 36% 1 1.2 6.8 55.8 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9956, quality 0.461)	`market_value_eur=4900000` `quality_factor=0.4609` `boost_factor=0.9956` `reference_quality=0.505` `history_matches=10` `history_shrink=0.3333`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0361)	`blend_weight=0.0361` `history_matches=10` `season_overlap_discount=1.0` `per90_to_match_factor=0.8432` `prior_reliability=0.1667` `competition=La Liga`	fouls: 1.1742 -> 1.2049 onTargetScoringAttempt: 0.5056 -> 0.5358 wasFouled: 0.9373 -> 0.9156 totalShots: 1.5213 -> 1.5391 interceptionWon: 0.3462 -> 0.3581 goals: 0.1438 -> 0.1508 wonTackle: 1.5078 -> 1.5143
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Santi Comesaña', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.333, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.901, 'skill_edge': -0.0194, 'height_edge': -0.048, 'attacker_skill': 0.4716, 'defender_skill': 0.5146, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Santi Comesaña', 'market_value': 8400000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5146}], 'xg_override': 0.1078}	totalShots: 1.5515 -> 1.3979 shotOffTarget: 1.0157 -> 0.9151 aerialWon: 0.9722 -> 0.9 onTargetScoringAttempt: 0.5358 -> 0.4828 bigChanceMissed: 0.1939 -> 0.1747 goals: 0.1508 -> 0.1359 expectedGoals: 0.1196 -> 0.1078 expectedGoalsOnTarget: 0.0709 -> 0.0639
`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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.1078 -> 0.1275 expected_assists: 0.0884 -> 0.0972
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 87.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_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=0.1197` `goal_rate=0.1359` `scorer_weight=0.1502`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0926` `assist_rate=0.086` `provider_weight=0.0955`	-

Gabriel Moscardo M 69 0 0.09 0.02 497% 1 0.2 6.7 27.6 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 0.9981, quality 0.493)	`market_value_eur=7500000` `quality_factor=0.4927` `boost_factor=0.9981` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0108)	`blend_weight=0.0108` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.7636` `prior_reliability=0.0333` `competition=La Liga`	onTargetScoringAttempt: 0.288 -> 0.3014 wonTackle: 0.5002 -> 0.5113 totalShots: 0.9174 -> 0.924 fouls: 0.5885 -> 0.5821
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Santi Comesaña', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.389, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9842, 'skill_edge': -0.0027, 'height_edge': -0.008, 'attacker_skill': 0.5085, 'defender_skill': 0.5146, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Santi Comesaña', 'market_value': 8400000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5146}], 'xg_override': 0.0778}	totalShots: 0.9308 -> 0.9161 shotOffTarget: 0.6294 -> 0.6195
`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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0778 -> 0.092
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 72.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0879` `goal_rate=0.0853` `scorer_weight=0.0974`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.028` `assist_rate=0.0401` `provider_weight=0.0338`	-

Edu Expósito M 83 0 0.11 0.08 32% 1 1.4 7.1 65.8 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9986, quality 0.456)	`market_value_eur=4500000` `quality_factor=0.456` `boost_factor=0.9986` `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=0.9208` `prior_reliability=0.18` `competition=La Liga`	totalCross: 4.1268 -> 4.0912 totalShots: 1.3283 -> 1.3486 fouls: 1.2427 -> 1.2363
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Juan Foyth', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.39, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.868, 'skill_edge': -0.0418, 'height_edge': -0.048, 'attacker_skill': 0.456, 'defender_skill': 0.5489, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Juan Foyth', 'market_value': 8600000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.5489}], 'xg_override': 0.0944}	totalShots: 1.3486 -> 1.1706 aerialWon: 0.7692 -> 0.9 shotOffTarget: 0.9196 -> 0.7982 onTargetScoringAttempt: 0.4079 -> 0.3541 goals: 0.1406 -> 0.122 expectedGoals: 0.1088 -> 0.0944 expectedGoalsOnTarget: 0.0883 -> 0.0766
`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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0944 -> 0.1116 expected_assists: 0.1504 -> 0.1652
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1056` `goal_rate=0.122` `scorer_weight=0.1329`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1523` `assist_rate=0.0977` `provider_weight=0.1322`	-

Quilindschy Hartman D 87 0 0.02 0.01 190% 0 0.2 6.7 30.8 26 FBref Prior D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0017, quality 0.541)	`market_value_eur=11600000` `quality_factor=0.5411` `boost_factor=1.0017` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Gerard Moreno', '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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.0723 -> 0.0795
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.018` `goal_rate=0.0` `scorer_weight=0.0146`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0764` `assist_rate=0.1128` `provider_weight=0.0994`	-

Leandro Cabrera D 90 0 0.08 0.06 ok 1 1.1 6.9 61.9 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 0.9979, quality 0.437)	`market_value_eur=930000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Georges Mikautadze', '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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_goals: 0.0675 -> 0.0798
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 76.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0767` `goal_rate=0.0061` `scorer_weight=0.0638`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0294` `assist_rate=0.0` `provider_weight=0.0238`	-

Vanja Drkušić D 85 0 0.00 - n/a 0 0.0 6.7 23.2 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9945, quality 0.468)	`market_value_eur=5500000` `quality_factor=0.4683` `boost_factor=0.9945` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0282)	`blend_weight=0.0282` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.9401` `prior_reliability=0.0867` `competition=La Liga`	fouls: 0.5586 -> 0.604 wasFouled: 0.838 -> 0.8755 interceptionWon: 0.8702 -> 0.8457 wonTackle: 0.7267 -> 0.747 totalShots: 0.3686 -> 0.3582
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Georges Mikautadze', '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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 80.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0014` `assist_rate=0.0` `provider_weight=0.0014`	-

Omar El Hilali D 89 0 0.00 - n/a 0 0.0 6.8 61.4 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0025, quality 0.589)	`market_value_eur=15900000` `quality_factor=0.5889` `boost_factor=1.0025` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0130)	`blend_weight=0.013` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9856` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 0.7143 -> 0.705 wonTackle: 1.2058 -> 1.1987 totalCross: 3.0907 -> 3.0975 totalShots: 0.4036 -> 0.3984
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Tajon Buchanan', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	expected_assists: 0.1149 -> 0.1263
`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=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1186` `assist_rate=0.0778` `provider_weight=0.101`	-

Ángel Fortuño G 90 0 0.00 - n/a 0.0 7.2 9.3 33 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9887, quality 0.437)	`market_value_eur=290000` `quality_factor=0.4374` `boost_factor=0.9887` `reference_quality=0.505` `history_matches=4` `history_shrink=0.5556`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Georges Mikautadze, Alberto Moleiro', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 2.046}`	-
`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 1.19 (squad xG sum 1.0072, xG scale 1.1825, xA scale 1.0990, team xA 0.95 = 0.80 x lambda)	`scoreline_reset=true` `team_lambda=1.191` `squad_xg_sum=1.0072` `squad_xa_sum=0.867` `team_expected_assists=0.9528` `team_xa_to_xg_ratio=0.8`	shots_faced: 19.4 -> 17.6 expected_saves: 4.74 -> 4.31 high_pressure_saves: 1.64 -> 1.48
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 89.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3186`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by 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=0.9085`	-

Team totals 1 1.19 11 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Marko Dmitrović	G	4.4m	13.1%	Market-value substitute prior
Clemens Riedel	D	13.6m	21.8%	Market-value substitute prior
Unai Núñez	D	13.6m	21.7%	Market-value substitute prior
Urko González	M	22.4m	31.5%	Market-value substitute prior
Cyril Ngonge	M	22.2m	50.7%	Market-value substitute prior
Tyrhys Dolan	F	25.7m	34.2%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Carlos Maciá vs Gabriel Moscardo will be the pivotal duel. Total antagonist xG — Home: 1.25, Away: 0.82. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.3% / 49.7%, dominance ratio 0.52, key duel: Carlos Maciá vs Gabriel Moscardo

Georges Mikautadze xG 0.42Alberto Moleiro xG 0.33Gerard Moreno xG 0.25Edu Expósito xG 0.09Javier Hernández xG 0.10Roberto Fernández xG 0.35

Summary

Antagonist matchup analysis for Villarreal vs Espanyol. Most likely scoreline: 2-1. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Villarreal 8W-1D-1L vs Espanyol over 10 meetings.

Tactical parity between 4-4-2 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Carlos Maciá vs Gabriel Moscardo will be the pivotal duel. Total antagonist xG — Home: 1.25, Away: 0.82. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Generated 2026-10-30 13:38:28 UTC · Soccer prediction reporting