Soccer predictions: actual data vs predicted data

Slate 20261016 · 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
Deportivo vs Levante LaLiga	1-1	Draw	35.0% / 27.4% / 37.6%	44.9%	50.4%	0.69	1.21 / 1.26	-	pending

Match detail

Deportivo vs Levante

LaLiga · 20261016 · 4-2-3-1 vs 4-3-3

Predicted 1-1Winner: DrawWinning H 1-0 (10.1%)Winning A 0-1 (10.5%)Confidence 0.69λ home/away 1.21 / 1.26Most-likely P 13.0%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Deportivo vs Levante. 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 1.208, Away 1.263). Final calibrated Poisson lambdas: Home 1.208, Away 1.263 (most likely score 1-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (6 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.21 / 1.26 Final λ (H/A) 1.21 / 1.26

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	Deportivo	Levante
League position	8.00	17.00
Points per game	1.30	1.09
Attack index	0.99	0.96
Defense (concede) index	1.08	0.96
Form multiplier	1.01	0.99
Standing λ multiplier	1.03	0.96

Lambda decomposition (how the goal rates were built)

Stage	Deportivo λ	Levante λ
Pre-competitive-floor	1.208	1.263
Pre-calibration (Micro-duels)	1.208	1.263
Final λ	1.208	1.263

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

Scoreline distribution & markets

Top 5 scorelines	P
1-1	13.0%
0-1	10.5%
1-0	10.1%
0-0	8.6%
1-2	8.1%

Home win	35.0%
Draw	27.4%
Away win	37.6%
Over 2.5	44.9%
BTTS yes	50.4%

Pregame fair line — favorite Levante (37.6%), fair total 2.47, fair spread -0.06

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.

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

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

Riki Rodríguez M 69 0 0.08 0.02 404% 1 0.2 6.8 26.9 12 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9899, quality 0.437)	`market_value_eur=1400000` `quality_factor=0.4374` `boost_factor=0.9899` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0152)	`blend_weight=0.0152` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.7643` `prior_reliability=0.0467` `competition=La Liga`	totalShots: 1.0446 -> 1.0287 totalCross: 0.1908 -> 0.2045 wasFouled: 0.4549 -> 0.4646 fouls: 0.6793 -> 0.6856 interceptionWon: 0.7189 -> 0.7246 onTargetScoringAttempt: 0.3677 -> 0.3621
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Daniel Requena', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.356, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9353, 'skill_edge': 0.0, 'height_edge': -0.044, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Daniel Requena', 'market_value': 1500000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}], 'xg_override': 0.0688}	aerialWon: 0.264 -> 0.9 totalShots: 1.039 -> 0.9718 shotOffTarget: 0.6769 -> 0.6331 onTargetScoringAttempt: 0.3621 -> 0.3387
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.0688 -> 0.082 expected_assists: 0.05 -> 0.0596
`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_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=0.0787` `goal_rate=0.0643` `scorer_weight=0.0789`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by 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=0.0676` `provider_weight=0.0701`	-

Diego Villares M 76 0 0.07 0.02 183% 1 0.2 6.9 23.6 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 0.9887, quality 0.437)	`market_value_eur=1000000` `quality_factor=0.4374` `boost_factor=0.9887` `reference_quality=0.505` `history_matches=4` `history_shrink=0.5556`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0169)	`blend_weight=0.0169` `history_matches=4` `season_overlap_discount=1.0` `per90_to_match_factor=0.8481` `prior_reliability=0.0467` `competition=La Liga`	wonTackle: 0.4147 -> 0.4486 fouls: 0.1905 -> 0.2077 totalShots: 0.6289 -> 0.6183 wasFouled: 0.6205 -> 0.61 totalCross: 0.3103 -> 0.3051
`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': 'Daniel Requena', 'matchup_zone': 'Holding Mid vs Central Mid — Midfield Anchor Duel', 'duel_win_rate': 0.4, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0, 'skill_edge': 0.0, 'height_edge': 0.0, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Daniel Requena', 'market_value': 1500000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}], 'xg_override': 0.0575}	aerialWon: 1.0223 -> 1.2
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.0575 -> 0.0685 expected_assists: 0.0482 -> 0.0574
`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_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=0.0662` `goal_rate=0.064` `scorer_weight=0.0726`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by 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=0.0477` `provider_weight=0.0571`	-

Giacomo Quagliata D 88 0 0.05 0.02 131% 0 0.4 6.7 42.7 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 0.9938, quality 0.451)	`market_value_eur=4099999` `quality_factor=0.4511` `boost_factor=0.9938` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0500)	`blend_weight=0.05` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.979` `prior_reliability=0.2` `competition=La Liga`	totalCross: 3.6583 -> 3.5896 totalShots: 0.4945 -> 0.4698 wonTackle: 0.7891 -> 0.766 interceptionWon: 1.049 -> 1.0618 onTargetScoringAttempt: 0.1585 -> 0.1506 wasFouled: 1.5255 -> 1.5308
`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': 'Thiago Fernández', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.039 -> 0.0465 expected_assists: 0.0798 -> 0.0951
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 73.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0454` `goal_rate=0.0` `scorer_weight=0.0372`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0907` `assist_rate=0.0` `provider_weight=0.0761`	-

Bright Ede D 90 0 0.08 0.02 282% 1 0.2 6.9 28.2 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 0.9958, quality 0.477)	`market_value_eur=6200000` `quality_factor=0.4769` `boost_factor=0.9958` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0477)	`blend_weight=0.0477` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1467` `competition=La Liga`	wonTackle: 0.677 -> 0.7097 wasFouled: 0.0 -> 0.0217 fouls: 0.2656 -> 0.2529
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roger Brugué', '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 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.068 -> 0.081
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0778` `goal_rate=0.0` `scorer_weight=0.0648`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0184` `assist_rate=0.0` `provider_weight=0.0149`	-

José María Giménez D 83 0 0.10 0.04 143% 1 0.5 6.9 43.8 25 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9982, quality 0.472)	`market_value_eur=5800000` `quality_factor=0.472` `boost_factor=0.9982` `reference_quality=0.505` `history_matches=23` `history_shrink=0.1786`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0031)	`blend_weight=0.0031` `history_matches=23` `season_overlap_discount=1.0` `per90_to_match_factor=0.9229` `prior_reliability=0.0267` `competition=La Liga`	fouls: 1.0819 -> 1.0928
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Roger Brugué', '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 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.0853 -> 0.1016
`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: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0966` `goal_rate=0.0` `scorer_weight=0.0813`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0258` `assist_rate=0.0505` `provider_weight=0.0326`	-

Ximo Navarro D 84 0 0.05 0.02 136% 1 0.3 6.7 37.3 12 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9916, quality 0.437)	`market_value_eur=95000` `quality_factor=0.4374` `boost_factor=0.9916` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0524)	`blend_weight=0.0524` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9301` `prior_reliability=0.1933` `competition=La Liga`	wonTackle: 1.3241 -> 1.2884 fouls: 0.435 -> 0.4626 wasFouled: 0.7555 -> 0.7663 totalCross: 1.4245 -> 1.4339 interceptionWon: 1.1163 -> 1.125 totalShots: 0.5175 -> 0.524
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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 Romero', '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 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.042 -> 0.05
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 72.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0488` `goal_rate=0.0` `scorer_weight=0.04`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0172` `assist_rate=0.0` `provider_weight=0.0138`	-

Leo Román G 90 0 0.00 - n/a 0.0 7.0 62.0 33 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0001, quality 0.507)	`market_value_eur=8700000` `quality_factor=0.5071` `boost_factor=1.0001` `reference_quality=0.505` `history_matches=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`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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 Romero, Roger Brugué', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2633}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 77.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.1945`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by 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=0.7859`	-

Luismi Cruz F 70 0 0.15 0.04 248% 1 0.4 6.9 43.1 21 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 0.9922, quality 0.437)	`market_value_eur=2100000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ifeanyi Ndukwe, Jeremy Toljan', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9066, 'skill_edge': -0.0035, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.4453, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ifeanyi Ndukwe', 'market_value': 3200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4531}, {'player': 'Jeremy Toljan', 'market_value': 1900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.1222}	totalShots: 1.249 -> 1.1324 shotOffTarget: 0.8045 -> 0.7294 onTargetScoringAttempt: 0.4445 -> 0.403 expectedGoals: 0.1348 -> 0.1222 expectedGoalsOnTarget: 0.1275 -> 0.1156 goals: 0.1253 -> 0.1136
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.1222 -> 0.1456 expected_assists: 0.1065 -> 0.1269
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 74.0)	`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=0.1355` `goal_rate=0.1136` `scorer_weight=0.1383`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1192` `assist_rate=0.1061` `provider_weight=0.1266`	-

Mario Soriano M 83 0 0.06 0.04 56% 1 0.8 7.2 47.8 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 0.9959, quality 0.470)	`market_value_eur=5600000` `quality_factor=0.4695` `boost_factor=0.9959` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0417)	`blend_weight=0.0417` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.9271` `prior_reliability=0.1667` `competition=La Liga`	totalCross: 2.6824 -> 2.6015 interceptionWon: 0.9612 -> 0.9366 fouls: 0.9052 -> 0.8829 wasFouled: 1.4449 -> 1.431 goalAssist: 0.1097 -> 0.1206 onTargetScoringAttempt: 0.2613 -> 0.2504 wonTackle: 0.5446 -> 0.5528
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Adrián de la Fuente', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.41, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8971, 'skill_edge': -0.01, 'height_edge': -0.06, 'attacker_skill': 0.4695, 'defender_skill': 0.4918, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Adrián de la Fuente', 'market_value': 5200000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4918}], 'xg_override': 0.0475}	aerialWon: 0.3549 -> 0.6 totalShots: 1.1311 -> 1.0147 shotOffTarget: 0.871 -> 0.7814 onTargetScoringAttempt: 0.2504 -> 0.2246 expectedGoalsOnTarget: 0.1333 -> 0.1196 goals: 0.0805 -> 0.0722 expectedGoals: 0.053 -> 0.0475
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.0475 -> 0.0566 expected_assists: 0.1386 -> 0.1649
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 75.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.055` `goal_rate=0.0722` `scorer_weight=0.0707`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.152` `assist_rate=0.1206` `provider_weight=0.1492`	-

Bil Nsongo F 73 1 0.27 0.10 170% 2 1.4 6.7 46.7 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 0.9955, quality 0.466)	`market_value_eur=5300000` `quality_factor=0.4659` `boost_factor=0.9955` `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=0.8152` `prior_reliability=0.1067` `competition=La Liga`	fouls: 0.8322 -> 0.8644 wonTackle: 0.9151 -> 0.9451 totalCross: 0.4002 -> 0.4167 totalShots: 1.9644 -> 1.952 goals: 0.2352 -> 0.2289
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ifeanyi Ndukwe, Jeremy Toljan', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9666, 'skill_edge': 0.0093, 'height_edge': -0.032, 'attacker_skill': 0.4659, 'defender_skill': 0.4453, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ifeanyi Ndukwe', 'market_value': 3200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4531}, {'player': 'Jeremy Toljan', 'market_value': 1900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.2265}	totalShots: 1.9603 -> 1.8948 shotOffTarget: 1.3131 -> 1.2692 onTargetScoringAttempt: 0.6472 -> 0.6256 expectedGoals: 0.2343 -> 0.2265 goals: 0.2289 -> 0.2213 bigChanceMissed: 0.2198 -> 0.2125
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.2265 -> 0.2698 expected_assists: 0.043 -> 0.0512
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 69.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2365` `goal_rate=0.2213` `scorer_weight=0.2647`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0499` `assist_rate=0.0` `provider_weight=0.041`	-

Yeremay Hernández F 77 0 0.22 0.08 175% 2 0.5 6.9 41.7 13 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0193, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0193` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0072)	`blend_weight=0.0072` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.8602` `prior_reliability=0.0267` `competition=La Liga`	wonTackle: 1.2213 -> 1.2436 totalOffside: 0.3285 -> 0.3417 totalShots: 1.6788 -> 1.6667 totalCross: 1.6797 -> 1.6676 wasFouled: 0.7699 -> 0.7799 interceptionWon: 0.7508 -> 0.7454
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ifeanyi Ndukwe, Jeremy Toljan', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.236, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0535, 'skill_edge': 0.0964, 'height_edge': -0.06, 'attacker_skill': 0.6595, 'defender_skill': 0.4453, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ifeanyi Ndukwe', 'market_value': 3200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4531}, {'player': 'Jeremy Toljan', 'market_value': 1900000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.1847}	totalShots: 1.6748 -> 1.7644 shotOffTarget: 1.1376 -> 1.1985 onTargetScoringAttempt: 0.5372 -> 0.5659 goals: 0.2129 -> 0.2243 expectedGoalsOnTarget: 0.2073 -> 0.2184 expectedGoals: 0.1753 -> 0.1847
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.21 (squad xG sum 1.0140, xG scale 1.1913, xA scale 1.1913, team xA 0.82 = 0.68 x lambda)	`scoreline_reset=true` `team_lambda=1.208` `squad_xg_sum=1.014` `squad_xa_sum=0.6883` `team_expected_assists=0.8199` `team_xa_to_xg_ratio=0.6788`	expected_goals: 0.1847 -> 0.22 expected_assists: 0.1212 -> 0.1444
`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_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=0.1975` `goal_rate=0.2243` `scorer_weight=0.2571`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1345` `assist_rate=0.1372` `provider_weight=0.1579`	-

Team totals 1 1.21 13 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Álvaro Ferllo	G	4.4m	10.9%	Market-value substitute prior
Lucas Noubi	D	13.6m	29.9%	Market-value substitute prior
Adrià Altimira	D	13.6m	29.9%	Market-value substitute prior
Marc Casadó	M	22.6m	52.9%	Market-value substitute prior
Lorenzo Amatucci	M	22.3m	51.5%	Market-value substitute prior
Jonathan Asp Jensen	F	25.4m	56.5%	Market-value substitute prior

Levante — 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

Iván Romero F 75 1 0.28 0.25 ok 2 1.7 7.0 59.9 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 0.9995, quality 0.491)	`market_value_eur=7400000` `quality_factor=0.4915` `boost_factor=0.9995` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0123)	`blend_weight=0.0123` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.835` `prior_reliability=0.1667` `competition=La Liga`	totalShots: 2.0603 -> 2.0723 wasFouled: 2.0205 -> 2.0121 interceptionWon: 0.4955 -> 0.4894
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ximo Navarro', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle', 'duel_win_rate': 0.488, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0122, 'skill_edge': 0.0243, 'height_edge': -0.016, 'attacker_skill': 0.4915, 'defender_skill': 0.4374, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ximo Navarro', 'market_value': 95000, 'role': 'RB', 'price_index': 0.7, 'adjusted_quality': 0.4374}], 'xg_override': 0.303}	totalShots: 2.0723 -> 2.0976 shotOffTarget: 1.1585 -> 1.1726 onTargetScoringAttempt: 0.899 -> 0.91 bigChanceMissed: 0.4337 -> 0.439
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.303 -> 0.281 expected_assists: 0.0594 -> 0.0693
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 75.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.245` `goal_rate=0.3766` `scorer_weight=0.3396`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.067` `assist_rate=0.0049` `provider_weight=0.0554`	-

Roger Brugué F 83 0 0.24 0.33 ok 2 1.9 6.9 45.8 21 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 0.9966, quality 0.437)	`market_value_eur=2800000` `quality_factor=0.4374` `boost_factor=0.9966` `reference_quality=0.505` `history_matches=25` `history_shrink=0.1667`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Bright Ede, José María Giménez', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.8713, 'skill_edge': -0.0276, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.4987, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Bright Ede', 'market_value': 6200000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5019}, {'player': 'José María Giménez', 'market_value': 5800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4955}], 'xg_override': 0.2567}	totalShots: 2.0599 -> 1.7948 shotOffTarget: 1.2149 -> 1.0585 onTargetScoringAttempt: 0.845 -> 0.7362 expectedGoalsOnTarget: 0.3742 -> 0.326 goals: 0.3409 -> 0.297 bigChanceMissed: 0.3119 -> 0.2718 expectedGoals: 0.2946 -> 0.2567
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2567 -> 0.2379 expected_assists: 0.0601 -> 0.0701
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 88.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2117` `goal_rate=0.297` `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=0` `assist_probability=0.0677` `assist_rate=0.1885` `provider_weight=0.0876`	-

Daniel Requena M 87 0 0.04 0.01 522% 1 0.2 6.8 32.4 10 FBref Prior M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9887, quality 0.437)	`market_value_eur=1500000` `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': 'Riki Rodríguez', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.494, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0647, 'skill_edge': 0.0, 'height_edge': 0.044, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Riki Rodríguez', 'market_value': 1400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0435}	aerialWon: 0.3103 -> 1.2 totalShots: 0.6183 -> 0.6583 shotOffTarget: 0.4492 -> 0.4783 onTargetScoringAttempt: 0.1691 -> 0.18
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.037 -> 0.0431
`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_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=0.0395` `goal_rate=0.0623` `scorer_weight=0.0484`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0422` `assist_rate=0.041` `provider_weight=0.0451`	-

Oriol Rey M 83 0 0.04 0.01 486% 1 0.2 6.8 34.6 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9968, quality 0.437)	`market_value_eur=1700000` `quality_factor=0.4374` `boost_factor=0.9968` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0203)	`blend_weight=0.0203` `history_matches=27` `season_overlap_discount=1.0` `per90_to_match_factor=0.9262` `prior_reliability=0.2` `competition=La Liga`	totalShots: 0.5612 -> 0.5498 wasFouled: 0.8068 -> 0.7967
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Riki Rodríguez', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.45, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0, 'skill_edge': 0.0, 'height_edge': 0.0, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Riki Rodríguez', 'market_value': 1400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0421}	aerialWon: 1.0009 -> 0.9
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0387 -> 0.0451
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 73.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0382` `goal_rate=0.0488` `scorer_weight=0.0418`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0441` `assist_rate=0.0506` `provider_weight=0.0512`	-

Jon Ander Olasagasti M 84 0 0.11 0.09 ok 1 1.0 6.9 62.2 31 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Riki Rodríguez', 'matchup_zone': 'CDM vs CDM', 'duel_win_rate': 0.425, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0073, 'skill_edge': 0.001, 'height_edge': 0.004, 'attacker_skill': 0.4396, 'defender_skill': 0.4374, 'attacker_role': 'CDM', 'attacker_mv_price_index': 0.85, 'defender_adjusted_parts': [{'player': 'Riki Rodríguez', 'market_value': 1400000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.1226}	aerialWon: 0.6155 -> 0.9 totalShots: 1.2409 -> 1.25 shotOffTarget: 0.7907 -> 0.7965
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1226 -> 0.1136 expected_assists: 0.1289 -> 0.1504
`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_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=0.1074` `goal_rate=0.1256` `scorer_weight=0.1156`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1396` `assist_rate=0.1136` `provider_weight=0.1375`	-

Manuel Sánchez D 88 0 0.00 0.01 47% 0 0.2 6.8 53.7 31 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9991, quality 0.479)	`market_value_eur=6400000` `quality_factor=0.4793` `boost_factor=0.9991` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Luismi Cruz', '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 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0691 -> 0.0806
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 78.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.004` `goal_rate=0.0023` `scorer_weight=0.0039`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0774` `assist_rate=0.0224` `provider_weight=0.0645`	-

Ifeanyi Ndukwe D 90 0 0.15 0.05 220% 1 0.1 6.8 22.1 9 FBref Prior D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9878, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.9878` `reference_quality=0.505` `history_matches=3` `history_shrink=0.625`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Yeremay Hernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1637 -> 0.1517
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 84.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1408` `goal_rate=0.384` `scorer_weight=0.1896`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0044` `assist_rate=0.0` `provider_weight=0.0041`	-

Adrián de la Fuente D 88 0 0.12 0.12 ok 2 1.4 6.9 64.5 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9987, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.9987` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0144)	`blend_weight=0.0144` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9726` `prior_reliability=0.2` `competition=La Liga`	wonTackle: 0.8525 -> 0.8449 onTargetScoringAttempt: 0.7804 -> 0.7738
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Mario Soriano', 'matchup_zone': 'Left Wing vs Right Back — Flank Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1252 -> 0.116 expected_assists: 0.1006 -> 0.1173
`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_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=0.1095` `goal_rate=0.3311` `scorer_weight=0.145`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1107` `assist_rate=0.0026` `provider_weight=0.0938`	-

Jeremy Toljan D 85 0 0.03 0.01 124% 0 0.2 6.6 59.1 31 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9979, quality 0.437)	`market_value_eur=1900000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0035)	`blend_weight=0.0035` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9412` `prior_reliability=0.0533` `competition=La Liga`	totalCross: 2.49 -> 2.4978
`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': 'Yeremay Hernández', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0732 -> 0.0854
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 74.0)	`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=0.0284` `goal_rate=0.0003` `scorer_weight=0.023`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0819` `assist_rate=0.1999` `provider_weight=0.1068`	-

Mathew Ryan G 90 0 0.00 0.01 100% 0.1 7.1 65.7 32 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9979, quality 0.437)	`market_value_eur=1700000` `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 0.0135)	`blend_weight=0.0135` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.9725 -> 2.9954
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Bil Nsongo, Yeremay Hernández', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2084}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `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 79.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.46`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by 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=0.8138`	-

Thiago Fernández F 71 0 0.13 0.05 174% 1 0.8 6.8 51.9 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 0.9973, quality 0.458)	`market_value_eur=4700000` `quality_factor=0.4585` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0133)	`blend_weight=0.0133` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.7867` `prior_reliability=0.1067` `competition=La Liga`	totalShots: 1.4649 -> 1.4582 onTargetScoringAttempt: 0.4821 -> 0.4757 interceptionWon: 0.5193 -> 0.5255 wasFouled: 0.4019 -> 0.3965
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Giacomo Quagliata', 'matchup_zone': 'Right Wing vs Left Back — Flank Battle', 'duel_win_rate': 0.466, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9788, 'skill_edge': -0.0064, 'height_edge': -0.008, 'attacker_skill': 0.4585, 'defender_skill': 0.4727, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Giacomo Quagliata', 'market_value': 4099999, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.4727}], 'xg_override': 0.1416}	totalShots: 1.4585 -> 1.4276 shotOffTarget: 0.9828 -> 0.962 onTargetScoringAttempt: 0.4757 -> 0.4656
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.3628, xG scale 0.9268, xA scale 1.1662, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.263` `squad_xg_sum=1.3628` `squad_xa_sum=0.704` `team_expected_assists=0.8209` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1416 -> 0.1312 expected_assists: 0.0911 -> 0.1062
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 74.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.123` `goal_rate=0.1949` `scorer_weight=0.164`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.1008` `assist_rate=0.0977` `provider_weight=0.1112`	-

Team totals 1 1.26 13 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Pablo Cunat Campos	G	4.4m	10.9%	Market-value substitute prior
Axel Tape	D	13.8m	31.1%	Market-value substitute prior
Matias Moreno	D	13.7m	30.5%	Market-value substitute prior
Carlos Álvarez	M	22.6m	31.9%	Market-value substitute prior
Enzo Bardeli	M	22.1m	50.5%	Market-value substitute prior
Etta Eyong	F	25.9m	58.5%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Mario Soriano vs Jon Ander Olasagasti will be the pivotal duel. Total antagonist xG — Home: 0.71, Away: 0.91. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Midfield — possession 50.1% / 49.9%, dominance ratio 0.51, key duel: Mario Soriano vs Jon Ander Olasagasti

Mario Soriano xG 0.05Yeremay Hernández xG 0.18Luismi Cruz xG 0.12Iván Romero xG 0.30Thiago Fernández xG 0.14Roger Brugué xG 0.26

Summary

Antagonist matchup analysis for Deportivo vs Levante. Most likely scoreline: 1-1. Lambdas derived from 6 home and 6 away individual player duels. Head-to-head: Deportivo 3W-4D-3L vs Levante 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 — Mario Soriano vs Jon Ander Olasagasti will be the pivotal duel. Total antagonist xG — Home: 0.71, Away: 0.91. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Generated 2026-10-16 15:24:46 UTC · Soccer prediction reporting