Soccer predictions: actual data vs predicted data

Slate 20261023 · 2 match(es)

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

All matches overview

Match	Score	Winner	H / D / A	O2.5	BTTS	Conf	λ H/A	Actual	Result
Alavés vs Málaga LaLiga	1-0	Alavés	45.2% / 29.2% / 25.6%	35.7%	41.6%	0.72	1.26 / 0.87	-	pending
Ipswich vs Forest Premier League	0-1	Forest	28.6% / 24.7% / 46.7%	54.0%	56.6%	0.72	1.22 / 1.62	-	pending

Match detail

Alavés vs Málaga

LaLiga · 20261023 · 5-3-2 vs 4-4-2

Predicted 1-0Winner: AlavésWinning H 1-0 (14.9%)Winning A 0-1 (10.3%)Confidence 0.72λ home/away 1.26 / 0.87Most-likely P 14.9%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Alavés vs Málaga. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 5-3-2 vs 4-4-2 (duel lambdas: Home 1.231, Away 0.888). Final calibrated Poisson lambdas: Home 1.257, Away 0.869 (most likely score 1-0).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (6 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.23 / 0.89 Final λ (H/A) 1.26 / 0.87

FBref Team Priors: Deportivo Alavés (Gls/90: 1.6666666666666667, GA/90: 1.67 → E[λ]: 0.407) vs Málaga CF (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.412) | 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	Alavés	Málaga
League position	7.00	20.00
Points per game	1.28	0.81
Attack index	1.02	0.72
Defense (concede) index	1.08	0.93
Form multiplier	1.03	0.97
Standing λ multiplier	1.05	0.85

Lambda decomposition (how the goal rates were built)

Stage	Alavés λ	Málaga λ
FBref Squad Prior E[λ] (weight 0.228)	0.407	0.412
Pre-competitive-floor	1.257	0.869
Pre-calibration (Micro-duels)	1.231	0.888
Final λ	1.257	0.869

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
1-0	14.9%
1-1	13.1%
0-0	12.0%
0-1	10.3%
2-0	9.4%

Home win	45.2%
Draw	29.2%
Away win	25.6%
Over 2.5	35.7%
BTTS yes	41.6%

Pregame fair line — favorite Alavés (45.2%), fair total 2.13, fair spread 0.39

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.

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

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

Lucas Boyé F 78 1 0.32 0.34 ok 2 2.1 6.8 61.9 27 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9986, quality 0.466)	`market_value_eur=5300000` `quality_factor=0.4659` `boost_factor=0.9986` `reference_quality=0.505` `history_matches=37` `history_shrink=0.119`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0083)	`blend_weight=0.0083` `history_matches=37` `season_overlap_discount=1.0` `per90_to_match_factor=0.8649` `prior_reliability=0.1067` `competition=La Liga`	wonTackle: 1.1633 -> 1.176 wasFouled: 1.6954 -> 1.6903
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ángel Recio, Fernando Calero', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.209, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0129, 'skill_edge': 0.0128, 'height_edge': -0.004, 'attacker_skill': 0.4659, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ángel Recio', 'market_value': 1000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Fernando Calero', 'market_value': 2100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.3169}	totalShots: 2.1359 -> 2.1635 shotOffTarget: 1.3588 -> 1.3763 onTargetScoringAttempt: 0.7748 -> 0.7848 expectedGoalsOnTarget: 0.4579 -> 0.4638
`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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 77.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2704` `goal_rate=0.3514` `scorer_weight=0.3448`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0605` `assist_rate=0.0068` `provider_weight=0.0499`	-

Mariano Díaz F 67 0 0.23 0.08 179% 2 0.6 6.7 31.8 22 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9958, quality 0.437)	`market_value_eur=480000` `quality_factor=0.4374` `boost_factor=0.9958` `reference_quality=0.505` `history_matches=19` `history_shrink=0.2083`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ángel Recio, Fernando Calero', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.184, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9765, 'skill_edge': 0.0, 'height_edge': -0.016, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ángel Recio', 'market_value': 1000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Fernando Calero', 'market_value': 2100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.2317}	totalShots: 1.6552 -> 1.6163 shotOffTarget: 0.984 -> 0.9609 onTargetScoringAttempt: 0.6711 -> 0.6553 bigChanceMissed: 0.4077 -> 0.3981 expectedGoals: 0.2373 -> 0.2317 goals: 0.2181 -> 0.213
`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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 91.0)	`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=0.2058` `goal_rate=0.213` `scorer_weight=0.2151`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0525` `assist_rate=0.1733` `provider_weight=0.0674`	-

Denis Suárez M 72 0 0.08 0.03 179% 1 0.2 7.0 55.0 28 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9976, quality 0.437)	`market_value_eur=1100000` `quality_factor=0.4374` `boost_factor=0.9976` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0060)	`blend_weight=0.006` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.7968` `prior_reliability=0.08` `competition=La Liga`	totalCross: 3.7138 -> 3.7476 fouls: 0.6893 -> 0.6972
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Dani Lorenzo', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.42, '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': 'Dani Lorenzo', 'market_value': 2300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}], 'xg_override': 0.081}	aerialWon: 0.1102 -> 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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.1578 -> 0.1686
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 74.0)	`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=0.0774` `goal_rate=0.0958` `scorer_weight=0.0897`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1552` `assist_rate=0.1311` `provider_weight=0.1469`	-

Antonio Blanco M 83 0 0.04 0.04 ok 1 1.0 6.9 64.4 32 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0004, quality 0.519)	`market_value_eur=9700000` `quality_factor=0.5189` `boost_factor=1.0004` `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=0.9257` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.3659 -> 1.3802 fouls: 1.7532 -> 1.7665 totalShots: 0.5878 -> 0.5963 totalCross: 1.1384 -> 1.1437
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Dani Lorenzo', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.462, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0623, 'skill_edge': 0.0424, 'height_edge': 0.0, 'attacker_skill': 0.5316, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Dani Lorenzo', 'market_value': 2300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}], 'xg_override': 0.0432}	aerialWon: 0.3891 -> 0.9 totalShots: 0.5963 -> 0.6334 shotOffTarget: 0.4137 -> 0.4395 onTargetScoringAttempt: 0.1718 -> 0.1825
`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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 78.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0421` `goal_rate=0.0458` `scorer_weight=0.0442`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0729` `assist_rate=0.0728` `provider_weight=0.077`	-

Pablo Ibáñez M 81 0 0.07 0.08 ok 1 1.2 6.9 63.4 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9984, quality 0.451)	`market_value_eur=4099999` `quality_factor=0.4511` `boost_factor=0.9984` `reference_quality=0.505` `history_matches=46` `history_shrink=0.098`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0127)	`blend_weight=0.0127` `history_matches=46` `season_overlap_discount=1.0` `per90_to_match_factor=0.9054` `prior_reliability=0.2` `competition=La Liga`	wasFouled: 2.2428 -> 2.2334 totalCross: 1.3067 -> 1.2977 totalShots: 0.9637 -> 0.9707 fouls: 1.757 -> 1.75
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dani Lorenzo, Carlos Dotor', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 73.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0684` `goal_rate=0.0765` `scorer_weight=0.0739`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0705` `assist_rate=0.087` `provider_weight=0.0846`	-

Abderrahman Rebbach F 81 0 0.08 0.04 93% 1 0.6 6.8 51.4 42 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=2400000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ángel Recio, Fernando Calero', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.953, 'skill_edge': 0.0, 'height_edge': -0.032, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ángel Recio', 'market_value': 1000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}, {'player': 'Fernando Calero', 'market_value': 2100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.0772}	totalShots: 0.9531 -> 0.9083 shotOffTarget: 0.6073 -> 0.5788 onTargetScoringAttempt: 0.3458 -> 0.3295
`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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0775 -> 0.0828
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 78.0)	`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=0.0739` `goal_rate=0.0899` `scorer_weight=0.0845`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0795` `assist_rate=0.0643` `provider_weight=0.0742`	-

Nicolás Valentini D 87 0 0.04 0.02 165% 1 0.4 6.8 41.2 10 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9910, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.991` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0020)	`blend_weight=0.002` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.9624` `prior_reliability=0.0067` `competition=La Liga`	fouls: 0.5754 -> 0.5933 totalShots: 0.699 -> 0.7132
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Chupete', '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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	-
`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=0.0439` `goal_rate=0.0` `scorer_weight=0.0359`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0265` `assist_rate=0.0` `provider_weight=0.0215`	-

Ville Koski D 89 0 0.10 0.04 155% 0 0.1 6.8 38.4 23 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9959, quality 0.454)	`market_value_eur=4300000` `quality_factor=0.4535` `boost_factor=0.9959` `reference_quality=0.505` `history_matches=14` `history_shrink=0.2632`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0331)	`blend_weight=0.0331` `history_matches=14` `season_overlap_discount=1.0` `per90_to_match_factor=0.9937` `prior_reliability=0.1933` `competition=La Liga`	fouls: 1.2765 -> 1.2343 wonTackle: 0.714 -> 0.7017 totalShots: 0.364 -> 0.352 wasFouled: 0.309 -> 0.2988 onTargetScoringAttempt: 0.2887 -> 0.2792
`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': 'Pablo Martínez', 'matchup_zone': 'LM vs CB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 68.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0981` `goal_rate=0.1258` `scorer_weight=0.118`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0141` `assist_rate=0.0` `provider_weight=0.0114`	-

Nahuel Tenaglia D 87 0 0.04 0.04 ok 1 0.7 6.8 61.7 32 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9980, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.998` `reference_quality=0.505` `history_matches=45` `history_shrink=0.1`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0130)	`blend_weight=0.013` `history_matches=45` `season_overlap_discount=1.0` `per90_to_match_factor=0.9624` `prior_reliability=0.2` `competition=La Liga`	totalCross: 1.413 -> 1.403 totalShots: 0.597 -> 0.6059 interceptionWon: 1.0899 -> 1.0966 fouls: 0.8157 -> 0.8218
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Rafa Garrido', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.26 (squad xG sum 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 77.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0423` `goal_rate=0.0696` `scorer_weight=0.054`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0395` `assist_rate=0.0` `provider_weight=0.0322`	-

Ángel Pérez M 81 0 0.17 0.07 129% 2 1.0 6.9 61.8 30 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9975, quality 0.457)	`market_value_eur=4600000` `quality_factor=0.4572` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=24` `history_shrink=0.1724`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0179)	`blend_weight=0.0179` `history_matches=24` `season_overlap_discount=1.0` `per90_to_match_factor=0.8982` `prior_reliability=0.16` `competition=La Liga`	totalCross: 3.9139 -> 3.8974 wasFouled: 0.8996 -> 0.8902 interceptionWon: 0.841 -> 0.8461
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Dani Lorenzo', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.46, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0584, 'skill_edge': 0.0118, 'height_edge': 0.028, 'attacker_skill': 0.4635, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Dani Lorenzo', 'market_value': 2300000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}], 'xg_override': 0.1692}	aerialWon: 0.2623 -> 1.1 totalShots: 1.6432 -> 1.7392 shotOffTarget: 1.0338 -> 1.0942 onTargetScoringAttempt: 0.6075 -> 0.643 goals: 0.174 -> 0.1842 expectedGoals: 0.1599 -> 0.1692 bigChanceMissed: 0.1473 -> 0.1559 expectedGoalsOnTarget: 0.1408 -> 0.149
`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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.1484 -> 0.1586
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 72.0)	`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=0.1549` `goal_rate=0.1842` `scorer_weight=0.1798`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1467` `assist_rate=0.1635` `provider_weight=0.1707`	-

Antonio Sivera G 90 0 0.00 - n/a 0.0 7.0 65.2 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 0.9990, quality 0.470)	`market_value_eur=5600000` `quality_factor=0.4695` `boost_factor=0.999` `reference_quality=0.505` `history_matches=47` `history_shrink=0.0962`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0125)	`blend_weight=0.0125` `history_matches=47` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.8969 -> 2.9024
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_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 Niño, Chupete', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.8883}`	-
`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 1.2639, xG scale 0.9946, xA scale 1.0687, team xA 0.82 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.257` `squad_xg_sum=1.2639` `squad_xa_sum=0.7645` `team_expected_assists=0.817` `team_xa_to_xg_ratio=0.65`	shots_faced: 8.4 -> 8.3 expected_saves: 2.05 -> 2.04 high_pressure_saves: 0.71 -> 0.7
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 85.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3303`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.7993`	-

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
Grégoire Swiderski	G	4.4m	10.9%	Market-value substitute prior
Youssef Enriquez	D	13.7m	30.4%	Market-value substitute prior
Victor Parada	D	13.6m	30.1%	Market-value substitute prior
Carles Aleñá	M	13.2m	69.2%	Market-value substitute prior
Ander Guevara	M	10.4m	69.2%	Market-value substitute prior
Toni Martínez	F	25.5m	33.8%	Market-value substitute prior

Málaga — 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

Chupete F 88 0 0.23 0.32 ok 2 1.9 6.8 51.9 11 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 1.0027, quality 0.531)	`market_value_eur=10700000` `quality_factor=0.5306` `boost_factor=1.0027` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0464)	`blend_weight=0.0464` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9778` `prior_reliability=0.2` `competition=La Liga`	totalCross: 0.8305 -> 0.7919 onTargetScoringAttempt: 0.8819 -> 0.8559 totalShots: 2.1644 -> 2.1851 totalOffside: 0.5683 -> 0.557 wonTackle: 0.5003 -> 0.5073 interceptionWon: 0.1269 -> 0.121
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ville Koski, Nicolás Valentini', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.233, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0488, 'skill_edge': 0.0312, 'height_edge': 0.002, 'attacker_skill': 0.5306, 'defender_skill': 0.4613, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ville Koski', 'market_value': 4300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4712}, {'player': 'Nicolás Valentini', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}], 'xg_override': 0.3043}	totalShots: 2.1851 -> 2.2917 shotOffTarget: 1.2825 -> 1.3451 onTargetScoringAttempt: 0.8559 -> 0.8977 bigChanceMissed: 0.3927 -> 0.4119 goals: 0.3032 -> 0.318 expectedGoals: 0.2901 -> 0.3043 expectedGoalsOnTarget: 0.2779 -> 0.2915
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3043 -> 0.2252 expected_assists: 0.036 -> 0.0287
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.2016` `goal_rate=0.318` `scorer_weight=0.2339`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0283` `assist_rate=0.0` `provider_weight=0.023`	-

Dani Lorenzo M 79 0 0.04 0.03 37% 1 0.3 7.0 54.9 10 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.437)	`market_value_eur=2300000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0300)	`blend_weight=0.03` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.8738` `prior_reliability=0.12` `competition=La Liga`	fouls: 0.9028 -> 0.8757 totalShots: 0.6276 -> 0.6088 wonTackle: 1.0944 -> 1.0761 interceptionWon: 0.6236 -> 0.634 totalCross: 0.2031 -> 0.197 onTargetScoringAttempt: 0.1911 -> 0.1854
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pablo Ibáñez', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.428, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9674, 'skill_edge': -0.0102, 'height_edge': -0.012, 'attacker_skill': 0.4374, 'defender_skill': 0.46, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Pablo Ibáñez', 'market_value': 4099999, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.46}], 'xg_override': 0.049}	aerialWon: 0.2389 -> 0.9 totalShots: 0.6219 -> 0.6017 shotOffTarget: 0.4365 -> 0.4223 onTargetScoringAttempt: 0.1854 -> 0.1794 bigChanceMissed: 0.1845 -> 0.1785
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.049 -> 0.0363 expected_assists: 0.0651 -> 0.0519
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 72.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0356` `goal_rate=0.0509` `scorer_weight=0.037`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0506` `assist_rate=0.0709` `provider_weight=0.0545`	-

Adrián Niño F 81 0 0.24 0.13 89% 2 1.4 6.8 50.4 7 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 0.9899, quality 0.437)	`market_value_eur=1900000` `quality_factor=0.4374` `boost_factor=0.9899` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ville Koski, Nicolás Valentini', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.195, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.993, 'skill_edge': -0.0108, 'height_edge': 0.006, 'attacker_skill': 0.4374, 'defender_skill': 0.4613, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ville Koski', 'market_value': 4300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4712}, {'player': 'Nicolás Valentini', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}], 'xg_override': 0.3221}	totalShots: 2.327 -> 2.3107 shotOffTarget: 1.3309 -> 1.3216 onTargetScoringAttempt: 0.996 -> 0.989
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3221 -> 0.2383 expected_assists: 0.0399 -> 0.0318
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 72.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.212` `goal_rate=0.3539` `scorer_weight=0.2587`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0313` `assist_rate=0.0` `provider_weight=0.0254`	-

Pablo Martínez M 82 0 0.08 0.06 32% 2 0.9 6.9 61.4 27 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9974, quality 0.439)	`market_value_eur=3100000` `quality_factor=0.4387` `boost_factor=0.9974` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0028)	`blend_weight=0.0028` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.9127` `prior_reliability=0.0333` `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': 'Ville Koski', 'matchup_zone': 'LM vs CB', 'duel_win_rate': 0.395, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9637, 'skill_edge': -0.0127, 'height_edge': -0.012, 'attacker_skill': 0.4429, 'defender_skill': 0.4712, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Ville Koski', 'market_value': 4300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4712}], 'xg_override': 0.1015}`	aerialWon: 0.3454 -> 1.1 totalShots: 1.5947 -> 1.5368 shotOffTarget: 1.1819 -> 1.139 onTargetScoringAttempt: 0.4128 -> 0.3978 bigChanceMissed: 0.1543 -> 0.1487 goals: 0.1498 -> 0.1444 expectedGoalsOnTarget: 0.1371 -> 0.1321
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1015 -> 0.0751 expected_assists: 0.1559 -> 0.1242
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 82.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0723` `goal_rate=0.1444` `scorer_weight=0.0939`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1168` `assist_rate=0.1395` `provider_weight=0.1143`	-

Carlos Dotor M 78 0 0.04 0.03 ok 1 0.4 6.9 56.4 11 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9922, quality 0.437)	`market_value_eur=1200000` `quality_factor=0.4374` `boost_factor=0.9922` `reference_quality=0.505` `history_matches=8` `history_shrink=0.3846`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0417)	`blend_weight=0.0417` `history_matches=8` `season_overlap_discount=1.0` `per90_to_match_factor=0.8649` `prior_reliability=0.1667` `competition=La Liga`	fouls: 1.208 -> 1.1721 wasFouled: 0.7497 -> 0.7185 totalCross: 0.0972 -> 0.122 wonTackle: 1.5 -> 1.524 totalShots: 0.6517 -> 0.6386 interceptionWon: 0.9623 -> 0.951 onTargetScoringAttempt: 0.1793 -> 0.1859
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Pablo Ibáñez', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.444, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9909, 'skill_edge': -0.0102, 'height_edge': 0.004, 'attacker_skill': 0.4374, 'defender_skill': 0.46, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Pablo Ibáñez', 'market_value': 4099999, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.46}], 'xg_override': 0.0507}	aerialWon: 0.2691 -> 1.1 totalShots: 0.6583 -> 0.6523
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0507 -> 0.0375 expected_assists: 0.0515 -> 0.041
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 85.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0368` `goal_rate=0.0544` `scorer_weight=0.0389`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0402` `assist_rate=0.0666` `provider_weight=0.0471`	-

David Larrubia F 84 0 0.07 0.07 ok 2 1.4 6.9 53.1 19 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 0.9971, quality 0.478)	`market_value_eur=6300000` `quality_factor=0.4781` `boost_factor=0.9971` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0371)	`blend_weight=0.0371` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=0.9374` `prior_reliability=0.16` `competition=La Liga`	totalCross: 1.4658 -> 1.4114 totalShots: 1.6074 -> 1.6497 wonTackle: 1.813 -> 1.8472 fouls: 0.8729 -> 0.855 totalOffside: 0.0776 -> 0.0892 onTargetScoringAttempt: 0.4808 -> 0.4922 wasFouled: 1.0488 -> 1.0389
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Ville Koski, Nicolás Valentini', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9376, 'skill_edge': 0.0075, 'height_edge': -0.05, 'attacker_skill': 0.4781, 'defender_skill': 0.4613, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Ville Koski', 'market_value': 4300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4712}, {'player': 'Nicolás Valentini', 'market_value': 3100000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4515}], 'xg_override': 0.0947}	totalShots: 1.6497 -> 1.5468 shotOffTarget: 1.1265 -> 1.0562 onTargetScoringAttempt: 0.4922 -> 0.4615 goals: 0.1235 -> 0.1158 expectedGoals: 0.101 -> 0.0947
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0947 -> 0.0701 expected_assists: 0.1569 -> 0.125
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 81.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0677` `goal_rate=0.1158` `scorer_weight=0.0803`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1175` `assist_rate=0.0` `provider_weight=0.1`	-

Adam Aznou D 90 0 0.08 0.02 329% 1 0.2 6.7 11.1 11 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9940, quality 0.477)	`market_value_eur=6200000` `quality_factor=0.4769` `boost_factor=0.994` `reference_quality=0.505` `history_matches=2` `history_shrink=0.7143`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Mariano Díaz', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.104 -> 0.077 expected_assists: 0.0945 -> 0.0753
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 67.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0741` `goal_rate=0.0` `scorer_weight=0.0616`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0725` `assist_rate=0.0` `provider_weight=0.0602`	-

Ángel Recio D 90 0 0.02 0.01 ok 1 0.6 6.9 54.7 11 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9928, quality 0.437)	`market_value_eur=1000000` `quality_factor=0.4374` `boost_factor=0.9928` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Lucas Boyé', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0212 -> 0.0157
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 65.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0156` `goal_rate=0.0` `scorer_weight=0.0126`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0067` `assist_rate=0.0` `provider_weight=0.0057`	-

Fernando Calero D 85 0 0.02 0.03 ok 0 0.3 6.8 54.5 21 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9971, quality 0.437)	`market_value_eur=2100000` `quality_factor=0.4374` `boost_factor=0.9971` `reference_quality=0.505` `history_matches=30` `history_shrink=0.1429`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Lucas Boyé', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0329 -> 0.0243
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 11 by projected rating, fifa_overall 81.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.024` `goal_rate=0.0` `scorer_weight=0.0194`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0093` `assist_rate=0.0` `provider_weight=0.0075`	-

Rafa Garrido D 88 0 0.00 0.00 45% 0 0.1 6.8 54.2 11 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9928, quality 0.437)	`market_value_eur=1400000` `quality_factor=0.4374` `boost_factor=0.9928` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Nahuel Tenaglia', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0257 -> 0.0205
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 79.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0015` `goal_rate=0.0` `scorer_weight=0.0014`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0203` `assist_rate=0.174` `provider_weight=0.0256`	-

Alfonso Herrero G 90 0 0.00 - n/a 0.0 6.9 58.0 11 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 0.9928, quality 0.437)	`market_value_eur=420000` `quality_factor=0.4374` `boost_factor=0.9928` `reference_quality=0.505` `history_matches=9` `history_shrink=0.3571`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0464)	`blend_weight=0.0464` `history_matches=9` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	saves: 2.8729 -> 2.9252 wasFouled: 0.2412 -> 0.23 fouls: 0.119 -> 0.1135
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Lucas Boyé, Mariano Díaz', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2308}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.87 (squad xG sum 1.1744, xG scale 0.7400, xA scale 0.7968, team xA 0.56 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.869` `squad_xg_sum=1.1744` `squad_xa_sum=0.7089` `team_expected_assists=0.5648` `team_xa_to_xg_ratio=0.65`	shots_faced: 11.7 -> 11.9 expected_saves: 2.86 -> 2.91 high_pressure_saves: 0.98 -> 1.01
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 75.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=0.91`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.5067`	-

Team totals 0 0.87 14 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Carlos Lopez	G	4.4m	10.9%	Market-value substitute prior
Jose Salinas	D	13.6m	29.9%	Market-value substitute prior
Diego Murillo	D	13.6m	29.9%	Market-value substitute prior
Jens-Lys Cajuste	M	22.1m	50.7%	Market-value substitute prior
Izan Merino	M	22.1m	50.3%	Market-value substitute prior
Joaquín Muñoz	F	25.3m	55.9%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Antonio Blanco vs Pablo Martínez will be the pivotal duel. Total antagonist xG — Home: 0.97, Away: 0.92. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.3% / 49.7%, dominance ratio 0.53, key duel: Antonio Blanco vs Pablo Martínez

Nahuel Tenaglia xG 0.05Ángel Pérez xG 0.17Antonio Blanco xG 0.04Pablo Martínez xG 0.10Dani Lorenzo xG 0.05Carlos Dotor xG 0.05

Summary

Antagonist matchup analysis for Alavés vs Málaga. Most likely scoreline: 1-0. Lambdas derived from 7 home and 6 away individual player duels. Head-to-head: Alavés 5W-3D-2L vs Málaga over 10 meetings.

Tactical parity between 5-3-2 and 4-4-2. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Antonio Blanco vs Pablo Martínez will be the pivotal duel. Total antagonist xG — Home: 0.97, Away: 0.92. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Ipswich vs Forest

Premier League · 20261023 · 4-2-3-1 vs 3-4-2-1

Predicted 0-1Winner: ForestWinning H 1-0 (7.0%)Winning A 0-1 (9.4%)Confidence 0.72λ home/away 1.22 / 1.62Most-likely P 9.4%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Ipswich vs Forest. 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 3-4-2-1 (duel lambdas: Home 1.262, Away 1.566). Final calibrated Poisson lambdas: Home 1.217, Away 1.622 (most likely score 0-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.26 / 1.57 Final λ (H/A) 1.22 / 1.62

FBref Team Priors: Ipswich Town (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 1.379) vs Nottingham Forest (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 1.379) | Blend Weight: 0.192

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Ipswich	Forest
League position	10.00	19.00
Points per game	1.32	1.01
Attack index	1.09	0.77
Defense (concede) index	0.91	1.24
Form multiplier	1.02	0.98
Standing λ multiplier	1.00	0.98

Lambda decomposition (how the goal rates were built)

Stage	Ipswich λ	Forest λ
FBref Squad Prior E[λ] (weight 0.192)	1.379	1.379
Pre-competitive-floor	1.217	1.622
Pre-calibration (Micro-duels)	1.262	1.566
Final λ	1.217	1.622

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

Scoreline distribution & markets

Top 5 scorelines	P
1-1	11.6%
0-1	9.4%
1-2	9.4%
0-2	7.7%
1-0	7.0%

Home win	28.6%
Draw	24.7%
Away win	46.7%
Over 2.5	54.0%
BTTS yes	56.6%

Pregame fair line — favorite Forest (46.7%), fair total 2.84, fair spread -0.41

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.

Ipswich — 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

Christian Walton G 90 0 0.00 - n/a 0.0 6.9 16.7 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 0.9873, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9873` `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': 'Liam Delap, Dan Ndoye', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.5662}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	shots_faced: 14.9 -> 15.4 expected_saves: 3.65 -> 3.77 high_pressure_saves: 1.25 -> 1.3
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 73.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.3594`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=0.8906`	-

Abdoul Ouattara M 88 0 0.05 0.01 379% 1 0.3 6.8 49.3 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 1.0113, quality 0.595)	`market_value_eur=16500000` `quality_factor=0.5953` `boost_factor=1.0113` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0054)	`blend_weight=0.0054` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9822` `prior_reliability=0.02` `competition=Premier League`	totalCross: 2.1818 -> 2.17 interceptionWon: 1.6383 -> 1.6294
`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': 'Morgan Gibbs-White', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.329, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.867, 'skill_edge': -0.1265, 'height_edge': 0.036, 'attacker_skill': 0.6044, 'defender_skill': 0.8855, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Morgan Gibbs-White', 'market_value': 76000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.8855}], 'xg_override': 0.0522}	aerialWon: 0.7272 -> 1.1 totalShots: 0.6988 -> 0.6059 shotOffTarget: 0.5401 -> 0.4683 onTargetScoringAttempt: 0.1587 -> 0.1376 expectedGoalsOnTarget: 0.144 -> 0.1248 expectedGoals: 0.0602 -> 0.0522 goals: 0.0535 -> 0.0464
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.072 -> 0.0814
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 73.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0493` `goal_rate=0.0464` `scorer_weight=0.0477`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0782` `assist_rate=0.1012` `provider_weight=0.1009`	-

Emersonn F 72 0 0.25 0.21 ok 2 1.2 6.7 39.7 12 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 1.0204, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0204` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0217)	`blend_weight=0.0217` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.7983` `prior_reliability=0.08` `competition=Premier League`	totalCross: 0.085 -> 0.0976 onTargetScoringAttempt: 0.828 -> 0.8384 totalOffside: 0.4605 -> 0.4505 wasFouled: 1.775 -> 1.7654 goals: 0.3216 -> 0.329 wonTackle: 0.3653 -> 0.3718 totalShots: 2.2272 -> 2.2213
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Murillo, Ousmane Diomande', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8728, 'skill_edge': -0.0845, 'height_edge': -0.002, 'attacker_skill': 0.6685, 'defender_skill': 0.8564, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Murillo', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}, {'player': 'Ousmane Diomande', 'market_value': 44000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8495}], 'xg_override': 0.2534}	totalShots: 2.2376 -> 1.953 shotOffTarget: 1.3992 -> 1.2212 onTargetScoringAttempt: 0.8384 -> 0.7318 bigChanceMissed: 0.471 -> 0.4111 goals: 0.329 -> 0.2872 expectedGoals: 0.2903 -> 0.2534 expectedGoalsOnTarget: 0.2101 -> 0.1834
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2534 -> 0.2458
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 74.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.2179` `goal_rate=0.2872` `scorer_weight=0.2732`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0376` `assist_rate=0.1354` `provider_weight=0.0479`	-

Daizen Maeda F 76 0 0.14 0.11 ok 1 0.4 6.7 43.4 16 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0059, quality 0.552)	`market_value_eur=12600000` `quality_factor=0.5525` `boost_factor=1.0059` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0307)	`blend_weight=0.0307` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.8406` `prior_reliability=0.1133` `competition=Premier League`	wonTackle: 1.0178 -> 1.0473 totalShots: 1.3966 -> 1.3844 fouls: 1.1475 -> 1.1578 goals: 0.2468 -> 0.2392 totalCross: 1.2115 -> 1.2047
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Murillo, Ousmane Diomande', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.7196, 'skill_edge': -0.1367, 'height_edge': -0.054, 'attacker_skill': 0.5525, 'defender_skill': 0.8564, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Murillo', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}, {'player': 'Ousmane Diomande', 'market_value': 44000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8495}], 'xg_override': 0.1468}	totalShots: 1.3952 -> 1.004 shotOffTarget: 0.8452 -> 0.6082 onTargetScoringAttempt: 0.55 -> 0.3958 expectedGoalsOnTarget: 0.2687 -> 0.1934 goals: 0.2392 -> 0.1721 expectedGoals: 0.204 -> 0.1468 bigChanceMissed: 0.1758 -> 0.1265
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 16 by projected rating, fifa_overall 78.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1326` `goal_rate=0.1721` `scorer_weight=0.1606`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0382` `assist_rate=0.0` `provider_weight=0.0312`	-

Julio Enciso M 81 0 0.14 0.10 40% 2 1.5 6.9 36.8 13 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0246, quality 0.702)	`market_value_eur=28000000` `quality_factor=0.7022` `boost_factor=1.0246` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0325)	`blend_weight=0.0325` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.9007` `prior_reliability=0.12` `competition=Premier League`	goalAssist: 0.1252 -> 0.1537 totalCross: 0.7836 -> 0.7581 totalShots: 2.3948 -> 2.4159 wonTackle: 0.4119 -> 0.431 interceptionWon: 0.5476 -> 0.5298 wasFouled: 1.4673 -> 1.4847 onTargetScoringAttempt: 0.7637 -> 0.7553 goals: 0.2266 -> 0.2192
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Murillo', 'matchup_zone': 'LW vs CB', 'duel_win_rate': 0.308, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.8346, 'skill_edge': -0.0725, 'height_edge': -0.04, 'attacker_skill': 0.7022, 'defender_skill': 0.8633, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Murillo', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}], 'xg_override': 0.1486}`	aerialWon: 0.1389 -> 0.9 totalShots: 2.4159 -> 2.0163 shotOffTarget: 1.6311 -> 1.3613 onTargetScoringAttempt: 0.7553 -> 0.6304 goals: 0.2192 -> 0.1829 expectedGoalsOnTarget: 0.1822 -> 0.1521 expectedGoals: 0.1781 -> 0.1486 bigChanceMissed: 0.1134 -> 0.0946
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.1255 -> 0.1418
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 78.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1342` `goal_rate=0.1829` `scorer_weight=0.169`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1322` `assist_rate=0.1537` `provider_weight=0.1646`	-

Abdul Fatawu Issahaku F 73 0 0.09 0.02 444% 1 0.4 6.9 35.6 21 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0223, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0223` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0315)	`blend_weight=0.0315` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.8151` `prior_reliability=0.1067` `competition=Premier League`	totalShots: 1.2315 -> 1.1927 fouls: 2.2352 -> 2.1969 interceptionWon: 1.1286 -> 1.1091 wonTackle: 1.0897 -> 1.1035 totalCross: 5.4782 -> 5.4661 onTargetScoringAttempt: 0.3755 -> 0.3637 goalAssist: 0.1693 -> 0.18 totalOffside: 0.1693 -> 0.18
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Murillo, Ousmane Diomande', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.18, 'pressing_faced': 'ULTRA_HIGH', 'numerical_situation': '1v2', 'xg_multiplier': 0.8375, 'skill_edge': -0.0845, 'height_edge': -0.026, 'attacker_skill': 0.6685, 'defender_skill': 0.8564, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Murillo', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}, {'player': 'Ousmane Diomande', 'market_value': 44000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8495}], 'xg_override': 0.092}	totalShots: 1.2196 -> 1.0214 shotOffTarget: 0.8559 -> 0.7168 onTargetScoringAttempt: 0.3637 -> 0.3046 goals: 0.1109 -> 0.0929 expectedGoals: 0.1099 -> 0.092
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.1209 -> 0.1367
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 82.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0853` `goal_rate=0.0929` `scorer_weight=0.0898`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1278` `assist_rate=0.18` `provider_weight=0.1709`	-

Exequiel Palacios M 86 0 0.03 - n/a 1 0.0 7.0 38.0 11 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0247, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0247` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0059)	`blend_weight=0.0059` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.9502` `prior_reliability=0.02` `competition=Premier League`	interceptionWon: 1.5437 -> 1.572 wasFouled: 1.0632 -> 1.0756 fouls: 1.257 -> 1.2683 wonTackle: 1.8654 -> 1.8731
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Liam Delap, Dan Ndoye, Morgan Gibbs-White', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.055 -> 0.0622
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 83.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0287` `goal_rate=0.0396` `scorer_weight=0.0326`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0603` `assist_rate=0.0519` `provider_weight=0.0604`	-

Florentino Luís M 76 0 0.03 0.00 524% 1 0.2 6.8 45.7 29 XGBoost M_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0030, quality 0.585)	`market_value_eur=15500000` `quality_factor=0.5846` `boost_factor=1.003` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Xaver Schlager', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0502 -> 0.0568
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 80.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0282` `goal_rate=0.0437` `scorer_weight=0.0337`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0552` `assist_rate=0.0493` `provider_weight=0.0563`	-

Leif Davis D 90 0 0.21 0.13 67% 1 0.5 6.7 35.8 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 1.0226, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0226` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0361)	`blend_weight=0.0361` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 3.0971 -> 3.0394 wonTackle: 0.8728 -> 0.8413 fouls: 0.8065 -> 0.7774 onTargetScoringAttempt: 0.339 -> 0.3629 totalShots: 0.7203 -> 0.7304 goals: 0.2388 -> 0.2482 interceptionWon: 0.8221 -> 0.8285
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Liam Delap', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2176 -> 0.211 expected_assists: 0.0831 -> 0.094
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 75.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1902` `goal_rate=0.2482` `scorer_weight=0.2351`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0897` `assist_rate=0.1337` `provider_weight=0.1175`	-

Issa Diop D 90 0 0.05 0.03 70% 0 0.1 6.9 34.9 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0013, quality 0.526)	`market_value_eur=10300000` `quality_factor=0.526` `boost_factor=1.0013` `reference_quality=0.505` `history_matches=20` `history_shrink=0.2`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0173)	`blend_weight=0.0173` `history_matches=20` `season_overlap_discount=1.0` `per90_to_match_factor=0.9972` `prior_reliability=0.1333` `competition=Premier League`	fouls: 0.6096 -> 0.625 totalShots: 0.4189 -> 0.4116 interceptionWon: 1.1139 -> 1.1205
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Liam Delap', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 75.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0514` `goal_rate=0.0519` `scorer_weight=0.0515`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0215` `assist_rate=0.0` `provider_weight=0.0174`	-

Dara O'Shea D 90 0 0.05 0.03 96% 1 0.2 6.9 39.3 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 1.0170, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.017` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0361)	`blend_weight=0.0361` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.2268 -> 1.2006 wonTackle: 1.1461 -> 1.1228 fouls: 0.9051 -> 0.9266 wasFouled: 0.7019 -> 0.7127 goals: 0.1909 -> 0.184 onTargetScoringAttempt: 0.1909 -> 0.184
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'James McAtee', 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.22 (squad xG sum 1.2552, xG scale 0.9696, xA scale 1.1308, team xA 0.79 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.217` `squad_xg_sum=1.2552` `squad_xa_sum=0.6996` `team_expected_assists=0.7911` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 75.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.049` `goal_rate=0.184` `scorer_weight=0.0628`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0396` `assist_rate=0.0` `provider_weight=0.0323`	-

Team totals 0 1.22 14 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Kjell Scherpen	G	4.8m	14.0%	Market-value substitute prior
Jacob Greaves	D	14.2m	23.0%	Market-value substitute prior
Cédric Kipré	D	13.6m	29.9%	Market-value substitute prior
Marcelino Núñez	M	22.5m	31.8%	Market-value substitute prior
Azor Matusiwa	M	22.4m	52.0%	Market-value substitute prior
Jack Clarke	F	22.7m	73.5%	Market-value substitute prior

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

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

Liam Delap F 80 0 0.38 0.18 112% 3 1.3 6.8 52.4 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 1.0100, quality 0.764)	`market_value_eur=37000000` `quality_factor=0.7641` `boost_factor=1.01` `reference_quality=0.505` `history_matches=34` `history_shrink=0.1282`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0017)	`blend_weight=0.0017` `history_matches=34` `season_overlap_discount=1.0` `per90_to_match_factor=0.8927` `prior_reliability=0.02` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Exequiel Palacios, Issa Diop', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.326, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0827, 'skill_edge': 0.0542, 'height_edge': 0.002, 'attacker_skill': 0.7641, 'defender_skill': 0.6436, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Exequiel Palacios', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}, {'player': 'Issa Diop', 'market_value': 10300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5652}], 'xg_override': 0.3611}	totalShots: 2.3423 -> 2.536 shotOffTarget: 1.4431 -> 1.5624 onTargetScoringAttempt: 0.8962 -> 0.9703 bigChanceMissed: 0.514 -> 0.5565 expectedGoals: 0.3335 -> 0.3611 goals: 0.2991 -> 0.3238 expectedGoalsOnTarget: 0.1415 -> 0.1532
`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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3611 -> 0.3807 expected_assists: 0.0629 -> 0.0751
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 77.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.3166` `goal_rate=0.3238` `scorer_weight=0.3462`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0723` `assist_rate=0.0` `provider_weight=0.0601`	-

Morgan Gibbs-White M 89 0 0.27 0.27 ok 3 1.9 7.1 63.4 35 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0117, quality 0.878)	`market_value_eur=76000000` `quality_factor=0.8781` `boost_factor=1.0117` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0090)	`blend_weight=0.009` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=0.9884` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 3.8286 -> 3.8119
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Exequiel Palacios', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.5, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.073, 'skill_edge': 0.0736, 'height_edge': -0.024, 'attacker_skill': 0.8855, 'defender_skill': 0.7219, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Exequiel Palacios', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}], 'xg_override': 0.2595}	aerialWon: 0.5532 -> 0.8 totalShots: 2.2767 -> 2.4429 shotOffTarget: 1.4838 -> 1.5921 onTargetScoringAttempt: 0.7929 -> 0.8508 bigChanceMissed: 0.3484 -> 0.3738 goals: 0.2969 -> 0.3186 expectedGoalsOnTarget: 0.2542 -> 0.2728 expectedGoals: 0.2418 -> 0.2595
`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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2595 -> 0.2737 expected_assists: 0.1882 -> 0.2246
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 83.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.2394` `goal_rate=0.3186` `scorer_weight=0.326`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.2012` `assist_rate=0.1809` `provider_weight=0.2177`	-

Dan Ndoye F 69 1 0.34 0.07 361% 2 0.7 6.8 31.6 32 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0100, quality 0.746)	`market_value_eur=34000000` `quality_factor=0.7455` `boost_factor=1.01` `reference_quality=0.505` `history_matches=31` `history_shrink=0.1389`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0084)	`blend_weight=0.0084` `history_matches=31` `season_overlap_discount=1.0` `per90_to_match_factor=0.7649` `prior_reliability=0.0933` `competition=Premier League`	totalCross: 0.9321 -> 0.9242 totalOffside: 0.6557 -> 0.6502
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Exequiel Palacios, Issa Diop', 'matchup_zone': 'Shadow Striker vs CDM + CB — Zone 14 Battle', 'duel_win_rate': 0.31, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0586, 'skill_edge': 0.0459, 'height_edge': -0.006, 'attacker_skill': 0.7455, 'defender_skill': 0.6436, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Exequiel Palacios', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}, {'player': 'Issa Diop', 'market_value': 10300000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.5652}], 'xg_override': 0.3189}	totalShots: 2.1178 -> 2.2419 shotOffTarget: 1.3131 -> 1.39 onTargetScoringAttempt: 0.8047 -> 0.8519 bigChanceMissed: 0.6749 -> 0.7144 goals: 0.3304 -> 0.3498 expectedGoals: 0.3012 -> 0.3189 expectedGoalsOnTarget: 0.2471 -> 0.2616
`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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3189 -> 0.3364 expected_assists: 0.0904 -> 0.1079
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 77.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.2857` `goal_rate=0.3498` `scorer_weight=0.3646`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1023` `assist_rate=0.0071` `provider_weight=0.0863`	-

Neco Williams D 89 0 0.09 0.05 66% 1 1.2 6.8 60.2 36 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0063, quality 0.710)	`market_value_eur=29000000` `quality_factor=0.71` `boost_factor=1.0063` `reference_quality=0.505` `history_matches=44` `history_shrink=0.102`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=44` `season_overlap_discount=1.0` `per90_to_match_factor=0.9926` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.3378 -> 1.3567 totalCross: 5.9255 -> 5.9082 interceptionWon: 1.0592 -> 1.0498 totalShots: 1.3934 -> 1.3855
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Abdul Fatawu Issahaku', '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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.1296 -> 0.1548
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 80.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0858` `goal_rate=0.0243` `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=0.1434` `assist_rate=0.0372` `provider_weight=0.1238`	-

Xaver Schlager M 85 0 0.07 0.03 151% 1 0.8 6.9 41.1 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 1.0082, quality 0.570)	`market_value_eur=14200000` `quality_factor=0.5704` `boost_factor=1.0082` `reference_quality=0.505` `history_matches=7` `history_shrink=0.4167`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0217)	`blend_weight=0.0217` `history_matches=7` `season_overlap_discount=1.0` `per90_to_match_factor=0.948` `prior_reliability=0.08` `competition=Premier League`	fouls: 1.2924 -> 1.2644 interceptionWon: 1.1501 -> 1.1252 wonTackle: 2.5141 -> 2.4939 totalCross: 0.0 -> 0.0171 totalShots: 1.0921 -> 1.1029
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Christian Walton', 'matchup_zone': 'Left Wingback vs Right Back — Overlapping Run', 'duel_win_rate': 0.439, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0276, 'skill_edge': 0.0788, 'height_edge': -0.06, 'attacker_skill': 0.6339, 'defender_skill': 0.4588, 'attacker_role': 'LWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Christian Walton', 'market_value': 2600000, 'role': 'GK', 'price_index': 0.55, 'adjusted_quality': 0.4588}], 'xg_override': 0.0622}	aerialWon: 0.5854 -> 0.9 totalShots: 1.1029 -> 1.1333 shotOffTarget: 0.8902 -> 0.9148 onTargetScoringAttempt: 0.1974 -> 0.2028
`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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0406 -> 0.0485
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 6 by projected rating, fifa_overall 78.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0635` `goal_rate=0.0671` `scorer_weight=0.0685`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0473` `assist_rate=0.0598` `provider_weight=0.0588`	-

James McAtee M 85 0 0.09 0.02 308% 1 0.5 6.9 28.4 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0072, quality 0.629)	`market_value_eur=19800000` `quality_factor=0.6291` `boost_factor=1.0072` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0150)	`blend_weight=0.015` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.9393` `prior_reliability=0.12` `competition=Premier League`	totalShots: 1.2874 -> 1.2681 fouls: 1.023 -> 1.0077 wasFouled: 1.0699 -> 1.0852 interceptionWon: 0.7481 -> 0.7369 wonTackle: 1.4205 -> 1.4148 onTargetScoringAttempt: 0.3495 -> 0.3443
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': "Dara O'Shea", 'matchup_zone': 'Right Wingback vs Left Back — Overlapping Run', 'duel_win_rate': 0.362, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.9443, 'skill_edge': -0.0059, 'height_edge': -0.032, 'attacker_skill': 0.7044, 'defender_skill': 0.7176, 'attacker_role': 'RWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': "Dara O'Shea", 'market_value': 21000000, 'role': 'LB', 'price_index': 0.7, 'adjusted_quality': 0.7176}], 'xg_override': 0.0873}	aerialWon: 0.4996 -> 1.1 totalShots: 1.2822 -> 1.2108 shotOffTarget: 0.9379 -> 0.8857 onTargetScoringAttempt: 0.3443 -> 0.3251 goals: 0.0927 -> 0.0875 expectedGoals: 0.0924 -> 0.0873
`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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.1256 -> 0.15
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 73.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.088` `goal_rate=0.0875` `scorer_weight=0.0922`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1393` `assist_rate=0.097` `provider_weight=0.1256`	-

Daniel Muñoz M 80 0 0.14 0.06 134% 1 0.7 6.8 51.7 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0058, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0058` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0033)	`blend_weight=0.0033` `history_matches=35` `season_overlap_discount=1.0` `per90_to_match_factor=0.8909` `prior_reliability=0.04` `competition=Premier League`	totalShots: 1.0923 -> 1.0984 totalCross: 1.6219 -> 1.6166
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Exequiel Palacios', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.456, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0089, 'skill_edge': -0.0179, 'height_edge': 0.024, 'attacker_skill': 0.6821, 'defender_skill': 0.7219, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Exequiel Palacios', 'market_value': 26000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.7219}], 'xg_override': 0.1312}	aerialWon: 2.14 -> 1.1 totalShots: 1.0984 -> 1.1082 shotOffTarget: 0.7239 -> 0.7303
`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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1312 -> 0.1384 expected_assists: 0.0825 -> 0.0985
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 82.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1292` `goal_rate=0.1448` `scorer_weight=0.1488`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0938` `assist_rate=0.0898` `provider_weight=0.1039`	-

Murillo D 88 0 0.12 0.05 122% 1 0.7 6.9 55.0 24 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0128, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0128` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0117)	`blend_weight=0.0117` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.9731` `prior_reliability=0.1333` `competition=Premier League`	totalShots: 1.3027 -> 1.2931 interceptionWon: 1.2309 -> 1.2222 fouls: 1.2219 -> 1.2133 wonTackle: 1.118 -> 1.1106 onTargetScoringAttempt: 0.4344 -> 0.4293
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Julio Enciso', 'matchup_zone': 'LW vs CB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.114 -> 0.1202 expected_assists: 0.0576 -> 0.0688
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 82.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.1133` `goal_rate=0.0042` `scorer_weight=0.0962`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0665` `assist_rate=0.0927` `provider_weight=0.086`	-

Ousmane Diomande D 87 0 0.06 0.02 196% 1 0.2 6.7 22.2 12 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 1.0443, quality 0.800)	`market_value_eur=44000000` `quality_factor=0.8002` `boost_factor=1.0443` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Emersonn', '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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 81.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0553` `goal_rate=0.0` `scorer_weight=0.0455`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0072` `assist_rate=0.0` `provider_weight=0.0064`	-

Jair D 84 0 0.02 0.02 ok 0 0.2 6.7 39.5 22 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0143, quality 0.686)	`market_value_eur=26000000` `quality_factor=0.6858` `boost_factor=1.0143` `reference_quality=0.505` `history_matches=14` `history_shrink=0.2632`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Daizen Maeda', '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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 80.0)	`match_squad_rank=17` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0169` `goal_rate=0.0` `scorer_weight=0.0136`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0081` `assist_rate=0.0` `provider_weight=0.0071`	-

Matz Sels G 90 0 0.00 - n/a 0.0 7.0 56.6 28 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 0.446)	`market_value_eur=3700000` `quality_factor=0.4461` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=38` `history_shrink=0.1163`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0101)	`blend_weight=0.0101` `history_matches=38` `season_overlap_discount=1.0` `per90_to_match_factor=0.9962` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.9332 -> 2.9237
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Emersonn, Julio Enciso', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.2622}`	-
`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 1.62 (squad xG sum 1.5378, xG scale 1.0548, xA scale 1.1941, team xA 1.05 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.622` `squad_xg_sum=1.5378` `squad_xa_sum=0.8829` `team_expected_assists=1.0543` `team_xa_to_xg_ratio=0.65`	shots_faced: 12.0 -> 11.6 expected_saves: 2.94 -> 2.84 high_pressure_saves: 1.01 -> 0.97
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 81.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=1.6318`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.992`	-

Team totals 1 1.62 15 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
John Victor	G	4.5m	11.3%	Market-value substitute prior
Nikola Milenković	D	14.6m	23.7%	Market-value substitute prior
Ola Aina	D	14.2m	23.0%	Market-value substitute prior
Omari Hutchinson	M	23.0m	54.6%	Market-value substitute prior
Ibrahim Sangaré	M	22.8m	32.3%	Market-value substitute prior
Callum Hudson Odoi	F	26.5m	61.2%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Julio Enciso vs Morgan Gibbs-White will be the pivotal duel. Total antagonist xG — Home: 0.69, Away: 1.22. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle.

Midfield — possession 49.9% / 50.1%, dominance ratio 0.48, key duel: Julio Enciso vs Morgan Gibbs-White

Julio Enciso xG 0.15Abdoul Ouattara xG 0.05Emersonn xG 0.25Liam Delap xG 0.36Dan Ndoye xG 0.32Xaver Schlager xG 0.06

Summary

Antagonist matchup analysis for Ipswich vs Forest. Most likely scoreline: 0-1. Lambdas derived from 5 home and 6 away individual player duels. Head-to-head: Ipswich 2W-1D-7L vs Forest over 10 meetings.

Tactical parity between 4-2-3-1 and 3-4-2-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Julio Enciso vs Morgan Gibbs-White will be the pivotal duel. Total antagonist xG — Home: 0.69, Away: 1.22. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle.

Generated 2026-10-23 13:40:00 UTC · Soccer prediction reporting