Soccer predictions: actual data vs predicted data

Slate 20261019 · 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
Tottenham vs Coventry Premier League	1-0	Tottenham	59.0% / 23.6% / 17.5%	47.1%	46.3%	0.75	1.74 / 0.82	-	pending
Getafe vs Rayo Vallecano LaLiga	0-1	Rayo Vallecano	31.0% / 31.3% / 37.7%	31.6%	39.4%	0.7	0.92 / 1.05	-	pending

Match detail

Tottenham vs Coventry

Premier League · 20261019 · 4-2-3-1 vs 5-4-1

Predicted 1-0Winner: TottenhamWinning H 1-0 (13.4%)Winning A 0-1 (6.3%)Confidence 0.75λ home/away 1.74 / 0.82Most-likely P 13.4%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Tottenham vs Coventry. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 5-4-1 (duel lambdas: Home 1.616, Away 0.928). Final calibrated Poisson lambdas: Home 1.735, Away 0.824 (most likely score 1-0).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.62 / 0.93 Final λ (H/A) 1.74 / 0.82

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	Tottenham	Coventry
League position	19.00	14.00
Points per game	0.92	1.17
Attack index	0.78	0.85
Defense (concede) index	1.08	1.01
Form multiplier	0.98	1.01
Standing λ multiplier	0.93	0.94

Lambda decomposition (how the goal rates were built)

Stage	Tottenham λ	Coventry λ
Pre-mismatch	1.651	0.908
Pre-competitive-floor	1.846	0.876
Pre-calibration (Micro-duels)	1.616	0.928
Final λ	1.735	0.824

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

Scoreline distribution & markets

Top 5 scorelines	P
1-0	13.4%
2-0	11.7%
1-1	11.1%
2-1	9.6%
0-0	7.8%

Home win	59.0%
Draw	23.6%
Away win	17.5%
Over 2.5	47.1%
BTTS yes	46.3%

Pregame fair line — favorite Tottenham (59.0%), fair total 2.56, fair spread 0.91

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.

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

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

Antonín Kinský G 90 0 0.00 - n/a 0.0 7.0 29.0 30 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0096, quality 0.620)	`market_value_eur=18900000` `quality_factor=0.6201` `boost_factor=1.0096` `reference_quality=0.505` `history_matches=13` `history_shrink=0.2778`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0241)	`blend_weight=0.0241` `history_matches=13` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 2.9662 -> 2.955
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Taiwo Awoniyi, Ephron Mason-Clark', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.9283}`	-
`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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	shots_faced: 8.8 -> 7.8 expected_saves: 2.15 -> 1.91 high_pressure_saves: 0.74 -> 0.66
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 77.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.8026`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0` `provider_weight=0.0` `squad_weight_total=1.0618`	-

Dominic Solanke F 78 1 0.48 0.14 245% 2 1.1 6.7 51.4 25 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0109, quality 0.694)	`market_value_eur=27000000` `quality_factor=0.6941` `boost_factor=1.0109` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0033)	`blend_weight=0.0033` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.8613` `prior_reliability=0.0267` `competition=Premier League`	wasFouled: 0.8276 -> 0.8392 totalOffside: 0.1756 -> 0.1822 totalShots: 2.1674 -> 2.1734
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Bobby Thomas, Ethan Pinnock', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.238, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0557, 'skill_edge': 0.0539, 'height_edge': -0.016, 'attacker_skill': 0.6941, 'defender_skill': 0.5744, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Bobby Thomas', 'market_value': 21000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7022}, {'player': 'Ethan Pinnock', 'market_value': 2800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4465}], 'xg_override': 0.3536}	totalShots: 2.1734 -> 2.2945 shotOffTarget: 1.3522 -> 1.4275 onTargetScoringAttempt: 0.8191 -> 0.8647 bigChanceMissed: 0.5209 -> 0.5499 expectedGoalsOnTarget: 0.3535 -> 0.3732 goals: 0.3392 -> 0.3581 expectedGoals: 0.3349 -> 0.3536
`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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3536 -> 0.479 expected_assists: 0.0502 -> 0.0691
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 79.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=1` `goal_probability=0.3806` `goal_rate=0.3581` `scorer_weight=0.4843`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0668` `assist_rate=0.0` `provider_weight=0.0553`	-

Sávio F 82 0 0.20 0.09 113% 3 0.9 7.0 39.1 30 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0148, quality 0.831)	`market_value_eur=52000000` `quality_factor=0.8309` `boost_factor=1.0148` `reference_quality=0.505` `history_matches=28` `history_shrink=0.1515`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Bobby Thomas, Ethan Pinnock', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.259, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0874, 'skill_edge': 0.1154, 'height_edge': -0.056, 'attacker_skill': 0.8309, 'defender_skill': 0.5744, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Bobby Thomas', 'market_value': 21000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7022}, {'player': 'Ethan Pinnock', 'market_value': 2800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4465}], 'xg_override': 0.1456}	totalShots: 1.9408 -> 2.1104 shotOffTarget: 1.3938 -> 1.5156 onTargetScoringAttempt: 0.5469 -> 0.5947 bigChanceMissed: 0.2677 -> 0.2911 expectedGoalsOnTarget: 0.1507 -> 0.1639 goals: 0.1494 -> 0.1625 expectedGoals: 0.1339 -> 0.1456
`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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1456 -> 0.1973 expected_assists: 0.1764 -> 0.2427
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 80.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1791` `goal_rate=0.1625` `scorer_weight=0.2143`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.2155` `assist_rate=0.0498` `provider_weight=0.1942`	-

Conor Gallagher M 78 0 0.13 0.08 65% 1 0.6 6.8 50.2 28 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0075, quality 0.725)	`market_value_eur=31000000` `quality_factor=0.7249` `boost_factor=1.0075` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0025)	`blend_weight=0.0025` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.862` `prior_reliability=0.0333` `competition=Premier League`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Caleb Yirenkyi, Matt Grimes', '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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0964 -> 0.1306 expected_assists: 0.0646 -> 0.0889
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 78.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1224` `goal_rate=0.0827` `scorer_weight=0.1184`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0851` `assist_rate=0.074` `provider_weight=0.0962`	-

Mohammed Kudus F 72 0 0.17 0.05 280% 1 0.6 6.8 36.9 22 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 1.0163, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0163` `reference_quality=0.505` `history_matches=24` `history_shrink=0.1724`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0022)	`blend_weight=0.0022` `history_matches=24` `season_overlap_discount=1.0` `per90_to_match_factor=0.8029` `prior_reliability=0.02` `competition=Premier League`	totalCross: 4.2735 -> 4.2939
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Bobby Thomas, Ethan Pinnock', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.255, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0805, 'skill_edge': 0.1108, 'height_edge': -0.056, 'attacker_skill': 0.8206, 'defender_skill': 0.5744, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Bobby Thomas', 'market_value': 21000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7022}, {'player': 'Ethan Pinnock', 'market_value': 2800000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4465}], 'xg_override': 0.1275}	totalShots: 1.2798 -> 1.3828 shotOffTarget: 0.8416 -> 0.9093 onTargetScoringAttempt: 0.433 -> 0.4679 goals: 0.1507 -> 0.1628 expectedGoals: 0.118 -> 0.1275 expectedGoalsOnTarget: 0.0938 -> 0.1014
`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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1275 -> 0.1728 expected_assists: 0.0998 -> 0.1373
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 81.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1587` `goal_rate=0.1628` `scorer_weight=0.2072`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1283` `assist_rate=0.0982` `provider_weight=0.1358`	-

Sandro Tonali M 85 0 0.11 0.06 89% 1 1.2 7.2 56.9 27 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0124, quality 0.884)	`market_value_eur=83000000` `quality_factor=0.8845` `boost_factor=1.0124` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0085)	`blend_weight=0.0085` `history_matches=41` `season_overlap_discount=1.0` `per90_to_match_factor=0.942` `prior_reliability=0.12` `competition=Premier League`	totalCross: 1.7914 -> 1.7851
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Bobby Thomas', 'matchup_zone': 'LW vs CB', 'duel_win_rate': 0.482, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0912, 'skill_edge': 0.082, 'height_edge': -0.02, 'attacker_skill': 0.8845, 'defender_skill': 0.7022, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Bobby Thomas', 'market_value': 21000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.7022}], 'xg_override': 0.0779}	aerialWon: 0.4991 -> 1.1 totalShots: 1.1395 -> 1.2434 shotOffTarget: 0.7625 -> 0.832 onTargetScoringAttempt: 0.3746 -> 0.4088 goals: 0.0945 -> 0.1031 expectedGoals: 0.0714 -> 0.0779
`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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0779 -> 0.1055 expected_assists: 0.1396 -> 0.192
`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` `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=0.1001` `goal_rate=0.1031` `scorer_weight=0.1263`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1747` `assist_rate=0.1273` `provider_weight=0.1795`	-

Lucas Bergvall M 65 0 0.11 0.03 320% 1 0.3 6.8 35.2 22 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0132, quality 0.786)	`market_value_eur=41000000` `quality_factor=0.7859` `boost_factor=1.0132` `reference_quality=0.505` `history_matches=27` `history_shrink=0.1562`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0034)	`blend_weight=0.0034` `history_matches=27` `season_overlap_discount=1.0` `per90_to_match_factor=0.725` `prior_reliability=0.0333` `competition=Premier League`	fouls: 1.7572 -> 1.7513
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Caleb Yirenkyi', 'matchup_zone': 'CAM vs CM', 'duel_win_rate': 0.487, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 1.0992, 'skill_edge': 0.0514, 'height_edge': 0.016, 'attacker_skill': 0.7964, 'defender_skill': 0.6821, 'attacker_role': 'CAM', 'attacker_mv_price_index': 0.95, 'defender_adjusted_parts': [{'player': 'Caleb Yirenkyi', 'market_value': 23000000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.6821}], 'xg_override': 0.083}	aerialWon: 0.4301 -> 1.2 totalShots: 0.7485 -> 0.8228 shotOffTarget: 0.4886 -> 0.5371 onTargetScoringAttempt: 0.2599 -> 0.2857 expectedGoals: 0.0755 -> 0.083 goals: 0.074 -> 0.0813
`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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.083 -> 0.1125 expected_assists: 0.0555 -> 0.0763
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 78.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.1064` `goal_rate=0.0813` `scorer_weight=0.1111`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0735` `assist_rate=0.0692` `provider_weight=0.0862`	-

Destiny Udogie D 79 0 0.01 0.00 145% 0 0.1 6.6 43.9 21 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0085, quality 0.669)	`market_value_eur=24000000` `quality_factor=0.6685` `boost_factor=1.0085` `reference_quality=0.505` `history_matches=24` `history_shrink=0.1724`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0022)	`blend_weight=0.0022` `history_matches=24` `season_overlap_discount=1.0` `per90_to_match_factor=0.882` `prior_reliability=0.02` `competition=Premier League`	totalCross: 1.1888 -> 1.1993
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Jay DaSilva', 'matchup_zone': 'LWB vs RW + RB'}`	-
`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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.028 -> 0.0385
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 17 by projected rating, fifa_overall 79.0)	`match_squad_rank=17` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `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=0.0095` `goal_rate=0.0` `scorer_weight=0.0083`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0378` `assist_rate=0.0` `provider_weight=0.0308`	-

Micky van de Ven D 88 0 0.10 0.05 105% 1 0.3 6.8 55.2 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0105, quality 0.821)	`market_value_eur=49000000` `quality_factor=0.8206` `boost_factor=1.0105` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0048)	`blend_weight=0.0048` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9762` `prior_reliability=0.0667` `competition=Premier League`	fouls: 0.8744 -> 0.8796
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Brandon Thomas-Asante', '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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0769 -> 0.1042
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 81.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.099` `goal_rate=0.0163` `scorer_weight=0.0834`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0124` `assist_rate=0.0059` `provider_weight=0.0118`	-

Jan Paul van Hecke D 90 0 0.18 0.08 141% 1 0.6 7.1 59.5 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 1.0114, quality 0.863)	`market_value_eur=65000000` `quality_factor=0.8627` `boost_factor=1.0114` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9976` `prior_reliability=0.1333` `competition=Premier League`	interceptionWon: 1.331 -> 1.3233 totalCross: 0.7619 -> 0.7549 wasFouled: 1.0373 -> 1.0323
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Brandon Thomas-Asante', '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 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1351 -> 0.1831 expected_assists: 0.0753 -> 0.1036
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 81.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1673` `goal_rate=0.1666` `scorer_weight=0.2143`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0984` `assist_rate=0.032` `provider_weight=0.0829`	-

Archie Gray M 82 0 0.08 0.04 103% 1 0.4 6.8 46.9 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 1.0106, quality 0.746)	`market_value_eur=34000000` `quality_factor=0.7455` `boost_factor=1.0106` `reference_quality=0.505` `history_matches=29` `history_shrink=0.1471`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0108)	`blend_weight=0.0108` `history_matches=29` `season_overlap_discount=1.0` `per90_to_match_factor=0.9134` `prior_reliability=0.1133` `competition=Premier League`	wasFouled: 0.7856 -> 0.8004 totalShots: 0.6865 -> 0.6791
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Caleb Yirenkyi', 'matchup_zone': 'Midfield lane'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 1 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=1`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 1.74 (squad xG sum 1.2805, xG scale 1.3549, xA scale 1.3756, team xA 1.13 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.735` `squad_xg_sum=1.2805` `squad_xa_sum=0.8198` `team_expected_assists=1.1278` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0604 -> 0.0818 expected_assists: 0.0524 -> 0.0721
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 77.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0785` `goal_rate=0.0555` `scorer_weight=0.0782`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0696` `assist_rate=0.0795` `provider_weight=0.0901`	-

Team totals 1 1.74 14 6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Guglielmo Vicario	G	5.0m	13.9%	Market-value substitute prior
Pedro Porro	D	15.0m	24.6%	Market-value substitute prior
Marcos Senesi	D	14.4m	23.5%	Market-value substitute prior
Mateus Fernandes	M	35.4m	53.4%	Market-value substitute prior
Xavi Simons	M	23.4m	56.3%	Market-value substitute prior
Omar Marmoush	F	26.9m	36.7%	Market-value substitute prior

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

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

Taiwo Awoniyi F 72 0 0.17 0.17 ok 2 0.6 6.7 35.9 26 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9994, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9994` `reference_quality=0.505` `history_matches=21` `history_shrink=0.1923`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0100)	`blend_weight=0.01` `history_matches=21` `season_overlap_discount=1.0` `per90_to_match_factor=0.8046` `prior_reliability=0.08` `competition=Premier League`	totalShots: 1.7697 -> 1.7781 totalOffside: 0.7141 -> 0.7204 onTargetScoringAttempt: 0.7504 -> 0.7559
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Micky van de Ven, Jan Paul van Hecke', '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': 0.7007, 'skill_edge': -0.1716, 'height_edge': -0.032, 'attacker_skill': 0.4939, 'defender_skill': 0.8752, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Micky van de Ven', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}, {'player': 'Jan Paul van Hecke', 'market_value': 65000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.887}], 'xg_override': 0.2113}	totalShots: 1.7781 -> 1.2459 shotOffTarget: 1.0193 -> 0.7142 onTargetScoringAttempt: 0.7559 -> 0.5297 expectedGoalsOnTarget: 0.3999 -> 0.2802 bigChanceMissed: 0.3785 -> 0.2652 expectedGoals: 0.3016 -> 0.2113 goals: 0.2839 -> 0.1989
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2113 -> 0.1672 expected_assists: 0.0573 -> 0.052
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 74.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.154` `goal_rate=0.1989` `scorer_weight=0.1593`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0507` `assist_rate=0.0` `provider_weight=0.0416`	-

Ephron Mason-Clark F 65 0 0.14 0.03 409% 1 0.2 6.7 21.2 18 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0146, quality 0.603)	`market_value_eur=17200000` `quality_factor=0.6027` `boost_factor=1.0146` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0130)	`blend_weight=0.013` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=0.7172` `prior_reliability=0.04` `competition=Premier League`	totalCross: 2.0022 -> 2.0694 wasFouled: 0.6862 -> 0.7084 totalShots: 1.647 -> 1.6256 fouls: 1.185 -> 1.2007 onTargetScoringAttempt: 0.5758 -> 0.5683
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Micky van de Ven, Jan Paul van Hecke', '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': 0.7433, 'skill_edge': -0.1226, 'height_edge': -0.052, 'attacker_skill': 0.6027, 'defender_skill': 0.8752, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Micky van de Ven', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}, {'player': 'Jan Paul van Hecke', 'market_value': 65000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.887}], 'xg_override': 0.1824}	totalShots: 1.6395 -> 1.2186 shotOffTarget: 1.0712 -> 0.7962 onTargetScoringAttempt: 0.5683 -> 0.4224 expectedGoals: 0.2454 -> 0.1824 goals: 0.2163 -> 0.1608 expectedGoalsOnTarget: 0.0456 -> 0.0339
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1824 -> 0.1442
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 14 by projected rating, fifa_overall 75.0)	`match_squad_rank=14` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1343` `goal_rate=0.1608` `scorer_weight=0.1308`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0433` `assist_rate=0.0` `provider_weight=0.0354`	-

Matt Grimes M 87 0 0.03 0.01 150% 0 0.4 6.8 37.2 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 0.9945, quality 0.465)	`market_value_eur=5200000` `quality_factor=0.4646` `boost_factor=0.9945` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0394)	`blend_weight=0.0394` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.9661` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 2.445 -> 2.539 fouls: 0.9768 -> 0.9383 wonTackle: 0.7013 -> 0.6737 interceptionWon: 0.3507 -> 0.3369 wasFouled: 0.7622 -> 0.7702 onTargetScoringAttempt: 0.1803 -> 0.1732 totalShots: 0.6479 -> 0.6414
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Antonín Kinský', 'matchup_zone': 'Left Mid vs Right Back — Wide Channel', 'duel_win_rate': 0.248, 'pressing_faced': 'MEDIUM', 'numerical_situation': '1v1', 'xg_multiplier': 0.7468, 'skill_edge': -0.1243, 'height_edge': -0.048, 'attacker_skill': 0.4717, 'defender_skill': 0.7479, 'attacker_role': 'LM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Antonín Kinský', 'market_value': 18900000, 'role': 'GK', 'price_index': 0.55, 'adjusted_quality': 0.7479}], 'xg_override': 0.0325}	totalShots: 0.6414 -> 0.479 shotOffTarget: 0.4675 -> 0.3491 aerialWon: 0.899 -> 1.0 onTargetScoringAttempt: 0.1732 -> 0.1293 goals: 0.0579 -> 0.0432 expectedGoals: 0.0435 -> 0.0325
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0325 -> 0.0257 expected_assists: 0.0723 -> 0.0656
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 76.0)	`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=0.0254` `goal_rate=0.0432` `scorer_weight=0.029`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0635` `assist_rate=0.0688` `provider_weight=0.0637`	-

Caleb Yirenkyi M 80 0 0.04 0.00 1090% 1 0.1 6.7 35.6 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 1.0211, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0211` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0295)	`blend_weight=0.0295` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.8834` `prior_reliability=0.1` `competition=Premier League`	wonTackle: 0.6408 -> 0.6219 interceptionWon: 0.3204 -> 0.3109 fouls: 1.987 -> 1.9805 wasFouled: 1.3762 -> 1.3703 onTargetScoringAttempt: 0.1828 -> 0.1774
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Conor Gallagher', 'matchup_zone': 'Central Mid vs Defensive Mid — Pressing/Creation Duel', 'duel_win_rate': 0.414, 'pressing_faced': 'HIGH', 'numerical_situation': '1v1', 'xg_multiplier': 0.9478, 'skill_edge': -0.0355, 'height_edge': 0.0, 'attacker_skill': 0.6821, 'defender_skill': 0.761, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Conor Gallagher', 'market_value': 31000000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.761}], 'xg_override': 0.047}	aerialWon: 1.4842 -> 1.1 totalShots: 0.5937 -> 0.5627 shotOffTarget: 0.4104 -> 0.389 onTargetScoringAttempt: 0.1774 -> 0.1681
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.047 -> 0.0372
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0365` `goal_rate=0.0518` `scorer_weight=0.039`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0416` `assist_rate=0.0578` `provider_weight=0.0473`	-

Brandon Thomas-Asante F 83 0 0.08 0.03 205% 1 0.5 6.7 35.5 13 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0123, quality 0.595)	`market_value_eur=16500000` `quality_factor=0.5953` `boost_factor=1.0123` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0217)	`blend_weight=0.0217` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.9181` `prior_reliability=0.0733` `competition=Premier League`	totalShots: 1.56 -> 1.5262 interceptionWon: 2.4752 -> 2.4939 totalCross: 1.0123 -> 1.0265 onTargetScoringAttempt: 0.4653 -> 0.4552 goalAssist: 0.3935 -> 0.385 wonTackle: 0.3935 -> 0.385
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Micky van de Ven, Jan Paul van Hecke', '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': 0.7502, 'skill_edge': -0.1259, 'height_edge': -0.044, 'attacker_skill': 0.5953, 'defender_skill': 0.8752, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Micky van de Ven', 'market_value': 49000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.8633}, {'player': 'Jan Paul van Hecke', 'market_value': 65000000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.887}], 'xg_override': 0.1053}	totalShots: 1.5499 -> 1.1627 shotOffTarget: 1.0947 -> 0.8212 onTargetScoringAttempt: 0.4552 -> 0.3415 goals: 0.1564 -> 0.1173 expectedGoals: 0.1403 -> 0.1053
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1053 -> 0.0832
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 73.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0798` `goal_rate=0.1173` `scorer_weight=0.0896`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0288` `assist_rate=0.385` `provider_weight=0.0365`	-

Jay DaSilva D 89 0 0.07 0.06 ok 1 0.4 6.8 44.4 14 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0049, quality 0.541)	`market_value_eur=11600000` `quality_factor=0.5411` `boost_factor=1.0049` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0394)	`blend_weight=0.0394` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.9939` `prior_reliability=0.1333` `competition=Premier League`	totalCross: 2.1099 -> 2.1247 goalAssist: 0.242 -> 0.2325 goals: 0.2057 -> 0.1976 interceptionWon: 0.6862 -> 0.6787 fouls: 0.332 -> 0.3385 onTargetScoringAttempt: 0.332 -> 0.3385
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Antonín Kinský, Destiny Udogie', 'matchup_zone': 'LWB vs RW + RB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0888 -> 0.0702 expected_assists: 0.0922 -> 0.0837
`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=0.0678` `goal_rate=0.1976` `scorer_weight=0.0877`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0803` `assist_rate=0.2325` `provider_weight=0.1046`	-

Bobby Thomas D 89 0 0.06 0.04 44% 1 0.9 6.8 40.5 11 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 1.0185, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0185` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0374)	`blend_weight=0.0374` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.9874` `prior_reliability=0.1267` `competition=Premier League`	interceptionWon: 1.1525 -> 1.1094 wasFouled: 1.2065 -> 1.2392 fouls: 0.7314 -> 0.7624 totalCross: 0.128 -> 0.1427 totalShots: 0.8614 -> 0.8491 wonTackle: 0.7537 -> 0.7449
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Sandro Tonali', 'matchup_zone': 'LW vs CB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0809 -> 0.0639
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 5 by projected rating, fifa_overall 74.0)	`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=0.0619` `goal_rate=0.0` `scorer_weight=0.0511`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0432` `assist_rate=0.0` `provider_weight=0.0354`	-

Ethan Pinnock D 87 0 0.01 0.00 210% 0 0.1 6.7 13.1 31 XGBoost D_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9928, quality 0.437)	`market_value_eur=2800000` `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': 'Sávio', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `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 75.0)	`match_squad_rank=11` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0133` `goal_rate=0.0` `scorer_weight=0.0107`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0057` `assist_rate=0.0` `provider_weight=0.0051`	-

Stephen Mfuni D 90 0 0.09 0.02 363% 1 0.2 6.6 13.9 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 0.9855, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9855` `reference_quality=0.505` `history_matches=2` `history_shrink=0.7143`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dominic Solanke', '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`	goals: 1.0 -> 0
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1105 -> 0.0873
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 18 by projected rating, fifa_overall 69.0)	`match_squad_rank=18` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0836` `goal_rate=0.5327` `scorer_weight=0.1091`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0036` `assist_rate=0.0` `provider_weight=0.0033`	-

Milan van Ewijk D 90 0 0.00 - n/a 0 0.0 6.7 36.3 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 1.0232, quality 0.660)	`market_value_eur=23000000` `quality_factor=0.6595` `boost_factor=1.0232` `reference_quality=0.505` `history_matches=5` `history_shrink=0.5`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0433)	`blend_weight=0.0433` `history_matches=5` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	wonTackle: 1.3352 -> 1.299 interceptionWon: 1.3217 -> 1.2861 wasFouled: 0.7449 -> 0.7126 totalCross: 0.9835 -> 1.0059 totalShots: 0.3741 -> 0.3579
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Sandro Tonali, Destiny Udogie', 'matchup_zone': 'RWB vs LW + LB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	expected_assists: 0.0583 -> 0.0529
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 13 by projected rating, fifa_overall 75.0)	`match_squad_rank=13` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0515` `assist_rate=0.0` `provider_weight=0.0423`	-

Carl Rushworth G 90 0 0.00 - n/a 0.0 7.1 36.6 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 1.0185, quality 0.641)	`market_value_eur=21000000` `quality_factor=0.6408` `boost_factor=1.0185` `reference_quality=0.505` `history_matches=6` `history_shrink=0.4545`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0394)	`blend_weight=0.0394` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.1333` `competition=Premier League`	saves: 3.0742 -> 3.0122 wasFouled: 0.1772 -> 0.1702
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Dominic Solanke, Sávio', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.616}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.82 (squad xG sum 1.0424, xG scale 0.7904, xA scale 0.9073, team xA 0.54 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.824` `squad_xg_sum=1.0424` `squad_xa_sum=0.5903` `team_expected_assists=0.5356` `team_xa_to_xg_ratio=0.65`	shots_faced: 15.4 -> 16.5 expected_saves: 3.77 -> 4.04 high_pressure_saves: 1.29 -> 1.39
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 76.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=0.8589`	-
`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=0.5255`	-

Team totals 0 0.82 11 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Daniel Bentley	G	4.4m	10.9%	Market-value substitute prior
Aurèle Amenda	D	14.2m	22.9%	Market-value substitute prior
Liam Kitching	D	14.1m	32.5%	Market-value substitute prior
Jack Rudoni	M	22.8m	53.5%	Market-value substitute prior
Victor Torp	M	23.9m	70.3%	Market-value substitute prior
Sidiki Cherif	F	26.1m	59.5%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~53% possession expected (Sandro Tonali vs Caleb Yirenkyi). Total antagonist xG — Home: 0.79, Away: 0.74. 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 52.7% / 47.3%, dominance ratio 0.60, key duel: Sandro Tonali vs Caleb Yirenkyi

Sandro Tonali xG 0.08Lucas Bergvall xG 0.08Sávio xG 0.15Brandon Thomas-Asante xG 0.11Taiwo Awoniyi xG 0.21Ephron Mason-Clark xG 0.18

Summary

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

Tactical parity between 4-2-3-1 and 5-4-1. Match outcome driven primarily by individual player quality. Home midfield dominates with ~53% possession expected (Sandro Tonali vs Caleb Yirenkyi). Total antagonist xG — Home: 0.79, Away: 0.74. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Getafe vs Rayo Vallecano

LaLiga · 20261019 · 3-4-2-1 vs 4-3-3

Predicted 0-1Winner: Rayo VallecanoWinning H 1-0 (12.7%)Winning A 0-1 (14.4%)Confidence 0.7λ home/away 0.92 / 1.05Most-likely P 14.4%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Getafe vs Rayo Vallecano. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 3-4-2-1 vs 4-3-3 (duel lambdas: Home 0.951, Away 1.021). Final calibrated Poisson lambdas: Home 0.924, Away 1.050 (most likely score 0-1).

Home Starters 11/11 XGBoost (11 FBref) Away Starters 11/11 XGBoost (7 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.95 / 1.02 Final λ (H/A) 0.92 / 1.05

FBref Team Priors: Getafe (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.328) vs Rayo Vallecano (Gls/90: 1.3333333333333333, GA/90: 1.33 → E[λ]: 0.326) | Blend Weight: 0.228

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Getafe	Rayo Vallecano
League position	14.00	13.00
Points per game	1.16	1.25
Attack index	0.73	0.96
Defense (concede) index	1.12	0.92
Form multiplier	0.99	1.00
Standing λ multiplier	0.92	0.95

Lambda decomposition (how the goal rates were built)

Stage	Getafe λ	Rayo Vallecano λ
FBref Squad Prior E[λ] (weight 0.228)	0.328	0.326
Pre-competitive-floor	0.924	1.050
Pre-calibration (Micro-duels)	0.951	1.021
Final λ	0.924	1.050

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
0-1	14.4%
0-0	14.0%
1-1	13.6%
1-0	12.7%
0-2	7.7%

Home win	31.0%
Draw	31.3%
Away win	37.7%
Over 2.5	31.6%
BTTS yes	39.4%

Pregame fair line — favorite Rayo Vallecano (37.7%), fair total 1.97, fair spread -0.13

Projected players vs season baseline

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

Getafe — 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

David Soria G 90 0 0.00 - n/a 0.0 7.0 68.3 31 FBref Prior G_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9980, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.998` `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=1.0` `prior_reliability=0.2` `competition=La Liga`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Sergio Camello, Álvaro García', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 1.0214}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `team_xa_to_xg_ratio=0.65`	shots_faced: 9.7 -> 10.0 expected_saves: 2.37 -> 2.45 high_pressure_saves: 0.82 -> 0.84
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 80.0)	`match_squad_rank=1` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=0.885`	-
`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=0.5917`	-

Djené D 83 0 0.00 - n/a 0 0.0 6.7 60.8 27 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0134)	`blend_weight=0.0134` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9193` `prior_reliability=0.1933` `competition=La Liga`	fouls: 0.7891 -> 0.7997 interceptionWon: 1.0599 -> 1.0669 wasFouled: 0.4172 -> 0.4116
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Jorge de Frutos', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `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 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=0.0003` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0099` `assist_rate=0.0` `provider_weight=0.0082`	-

Nemanja Gudelj M 86 0 0.07 0.03 115% 1 0.9 6.7 61.5 31 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=1900000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0010)	`blend_weight=0.001` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9574` `prior_reliability=0.0133` `competition=La Liga`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Unai López, Pathé Ismaël Ciss', 'matchup_zone': 'Central Mid vs Mid + CDM Pressing Trap', 'duel_win_rate': 0.294, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0647, 'skill_edge': 0.0, 'height_edge': 0.044, 'attacker_skill': 0.4374, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Unai López', 'market_value': 2600000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}, {'player': 'Pathé Ismaël Ciss', 'market_value': 1600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.0756}	aerialWon: 1.506 -> 1.2 totalShots: 0.8848 -> 0.942 shotOffTarget: 0.6309 -> 0.6717 onTargetScoringAttempt: 0.249 -> 0.2651
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `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 78.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0702` `goal_rate=0.0653` `scorer_weight=0.0668`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0416` `assist_rate=0.0491` `provider_weight=0.0453`	-

Francho Serrano M 86 0 0.06 0.01 444% 1 0.3 6.8 44.3 9 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 0.9910, 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 0.0355)	`blend_weight=0.0355` `history_matches=6` `season_overlap_discount=1.0` `per90_to_match_factor=0.955` `prior_reliability=0.12` `competition=La Liga`	totalCross: 1.0836 -> 1.1392 totalShots: 0.9111 -> 0.8788 interceptionWon: 0.8633 -> 0.8891 wonTackle: 0.1395 -> 0.1534 onTargetScoringAttempt: 0.26 -> 0.2508 fouls: 0.7869 -> 0.7778
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Jorge de Frutos', 'matchup_zone': 'Left Wingback vs Right Winger — Tracking Run Duel', 'duel_win_rate': 0.421, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.972, 'skill_edge': -0.035, 'height_edge': 0.016, 'attacker_skill': 0.4551, 'defender_skill': 0.533, 'attacker_role': 'LWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Jorge de Frutos', 'market_value': 10900000, 'role': 'RW', 'price_index': 1.0, 'adjusted_quality': 0.533}], 'xg_override': 0.0662}	aerialWon: 0.2271 -> 1.0 totalShots: 0.9019 -> 0.8767 shotOffTarget: 0.6511 -> 0.6329 onTargetScoringAttempt: 0.2508 -> 0.2438
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `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 79.0)	`match_squad_rank=5` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0617` `goal_rate=0.0547` `scorer_weight=0.0574`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0587` `assist_rate=0.0812` `provider_weight=0.0714`	-

Kiko Femenía D 67 0 0.02 0.03 ok 0 0.2 6.6 55.7 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 0.9973, quality 0.437)	`market_value_eur=525000` `quality_factor=0.4374` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0088)	`blend_weight=0.0088` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.745` `prior_reliability=0.1` `competition=La Liga`	totalCross: 1.7621 -> 1.7728 interceptionWon: 0.877 -> 0.8693
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Sergio Camello', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 18 by projected rating, fifa_overall 74.0)	`match_squad_rank=18` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0236` `goal_rate=0.0378` `scorer_weight=0.0281`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0607` `assist_rate=0.005` `provider_weight=0.0501`	-

Martín Satriano F 81 0 0.21 0.17 ok 2 1.7 6.8 63.1 31 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0012, quality 0.529)	`market_value_eur=10600000` `quality_factor=0.5295` `boost_factor=1.0012` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0189)	`blend_weight=0.0189` `history_matches=26` `season_overlap_discount=1.0` `per90_to_match_factor=0.8978` `prior_reliability=0.18` `competition=La Liga`	wasFouled: 1.7966 -> 1.8129 fouls: 1.8161 -> 1.8069 interceptionWon: 0.3459 -> 0.3394 onTargetScoringAttempt: 0.6325 -> 0.6268 wonTackle: 0.2655 -> 0.2605
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mujaid Sadick, Unai López', 'matchup_zone': 'Shadow Striker vs CB + Mid Cover — Layered Defense', 'duel_win_rate': 0.352, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.1064, 'skill_edge': 0.0324, 'height_edge': 0.04, 'attacker_skill': 0.5295, 'defender_skill': 0.4576, 'attacker_role': 'SS', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Mujaid Sadick', 'market_value': 4700000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4777}, {'player': 'Unai López', 'market_value': 2600000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}], 'xg_override': 0.2234}	totalShots: 1.8731 -> 2.0724 shotOffTarget: 1.2386 -> 1.3704 onTargetScoringAttempt: 0.6268 -> 0.6935 expectedGoals: 0.2019 -> 0.2234 expectedGoalsOnTarget: 0.1922 -> 0.2127 goals: 0.1725 -> 0.1909 bigChanceMissed: 0.1151 -> 0.1273
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2234 -> 0.215
`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 skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1935` `goal_rate=0.1909` `scorer_weight=0.1894`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0513` `assist_rate=0.1653` `provider_weight=0.0659`	-

Ramón Terrats M 82 0 0.18 0.07 147% 2 1.0 6.8 60.8 29 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9976, quality 0.440)	`market_value_eur=3200000` `quality_factor=0.4399` `boost_factor=0.9976` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0159)	`blend_weight=0.0159` `history_matches=36` `season_overlap_discount=1.0` `per90_to_match_factor=0.912` `prior_reliability=0.2` `competition=La Liga`	totalCross: 2.0692 -> 2.099 totalShots: 1.5424 -> 1.5664 wasFouled: 2.4836 -> 2.4924 interceptionWon: 0.8041 -> 0.7962
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Álvaro García', 'matchup_zone': 'Right Wingback vs Left Winger — Tracking Run Duel', 'duel_win_rate': 0.493, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 1.0776, 'skill_edge': 0.0088, 'height_edge': 0.044, 'attacker_skill': 0.4569, 'defender_skill': 0.4374, 'attacker_role': 'RWB', 'attacker_mv_price_index': 0.7, 'defender_adjusted_parts': [{'player': 'Álvaro García', 'market_value': 1500000, 'role': 'LW', 'price_index': 1.0, 'adjusted_quality': 0.4374}], 'xg_override': 0.1905}	totalShots: 1.5664 -> 1.688 shotOffTarget: 0.9822 -> 1.0584 onTargetScoringAttempt: 0.561 -> 0.6045 bigChanceMissed: 0.2056 -> 0.2216 goals: 0.1849 -> 0.1992 expectedGoals: 0.1768 -> 0.1905 expectedGoalsOnTarget: 0.1519 -> 0.1637
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1905 -> 0.1834
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 82.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1676` `goal_rate=0.1992` `scorer_weight=0.19`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1059` `assist_rate=0.0966` `provider_weight=0.1007`	-

Andrés García D 76 0 0.03 0.01 122% 1 0.4 6.6 46.3 22 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9991, quality 0.494)	`market_value_eur=7600000` `quality_factor=0.4939` `boost_factor=0.9991` `reference_quality=0.505` `history_matches=13` `history_shrink=0.2778`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0301)	`blend_weight=0.0301` `history_matches=13` `season_overlap_discount=1.0` `per90_to_match_factor=0.8491` `prior_reliability=0.1667` `competition=La Liga`	wonTackle: 1.2071 -> 1.2321 interceptionWon: 0.7188 -> 0.6972 fouls: 0.6506 -> 0.631 totalCross: 2.9733 -> 2.986 totalShots: 0.5797 -> 0.5924 wasFouled: 0.1355 -> 0.1416 onTargetScoringAttempt: 0.1875 -> 0.1819
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Álvaro García', 'matchup_zone': 'LW vs CB'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `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 73.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0308` `goal_rate=0.0` `scorer_weight=0.025`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0403` `assist_rate=0.0` `provider_weight=0.0329`	-

Johan Mojica D 85 0 0.03 0.02 68% 1 0.4 6.7 59.4 29 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9978, quality 0.437)	`market_value_eur=1400000` `quality_factor=0.4374` `boost_factor=0.9978` `reference_quality=0.505` `history_matches=42` `history_shrink=0.1064`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0092)	`blend_weight=0.0092` `history_matches=42` `season_overlap_discount=1.0` `per90_to_match_factor=0.9394` `prior_reliability=0.1333` `competition=La Liga`	totalCross: 6.6809 -> 6.7059 wasFouled: 1.4184 -> 1.4313
`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': 'Sergio Camello', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 76.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0263` `goal_rate=0.0` `scorer_weight=0.0214`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.1057` `assist_rate=0.0437` `provider_weight=0.0894`	-

Mario Martín M 81 0 0.11 0.08 ok 1 0.7 6.7 59.8 26 FBref Prior M_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost M_service raw output over 8 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0009, quality 0.531)	`market_value_eur=10700000` `quality_factor=0.5306` `boost_factor=1.0009` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0034)	`blend_weight=0.0034` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.9051` `prior_reliability=0.0467` `competition=La Liga`	wasFouled: 1.7552 -> 1.7667
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Unai López, Pathé Ismaël Ciss', 'matchup_zone': 'Central Mid vs Mid + CDM Pressing Trap', 'duel_win_rate': 0.302, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 1.0766, 'skill_edge': 0.0481, 'height_edge': 0.004, 'attacker_skill': 0.5444, 'defender_skill': 0.4374, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Unai López', 'market_value': 2600000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.4374}, {'player': 'Pathé Ismaël Ciss', 'market_value': 1600000, 'role': 'CDM', 'price_index': 0.85, 'adjusted_quality': 0.4374}], 'xg_override': 0.1114}	aerialWon: 1.9945 -> 1.0 totalShots: 1.1031 -> 1.1876 shotOffTarget: 0.7242 -> 0.7797 onTargetScoringAttempt: 0.3789 -> 0.4079 bigChanceMissed: 0.1608 -> 0.1731 expectedGoals: 0.1035 -> 0.1114 goals: 0.0796 -> 0.0857
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 8 by projected rating, fifa_overall 74.0)	`match_squad_rank=8` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.1017` `goal_rate=0.0857` `scorer_weight=0.0902`	-
`integer_assist_projection`	Team scoreline allocation skipped: 0 projected assists	`allocation_applied=false` `team_assists=0` `assists_allocated=0` `assist_probability=0.0431` `assist_rate=0.0772` `provider_weight=0.0551`	-

Abdel Abqar D 80 0 0.00 0.01 79% 0 0.1 6.6 51.2 18 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 0.9969, quality 0.441)	`market_value_eur=3300000` `quality_factor=0.4412` `boost_factor=0.9969` `reference_quality=0.505` `history_matches=26` `history_shrink=0.1613`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0070)	`blend_weight=0.007` `history_matches=26` `season_overlap_discount=1.0` `per90_to_match_factor=0.8872` `prior_reliability=0.0667` `competition=La Liga`	wasFouled: 1.6275 -> 1.6223
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Álvaro García', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 0 goals are handed out as whole numbers by integer_goal_projection / integer_assist_projection	`scoreline_reset=true` `team_goals=0`	-
`team_lambda_rescale`	Player expected_goals/expected_assists rescaled to unconditional contributions so squad sum equals team lambda 0.92 (squad xG sum 0.9597, xG scale 0.9628, xA scale 0.9905, team xA 0.60 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=0.924` `squad_xg_sum=0.9597` `squad_xa_sum=0.6064` `team_expected_assists=0.6006` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 79.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation skipped: 0 projected goals	`team_goals=0` `allocation_applied=false` `goals_allocated=0` `goal_probability=0.0014` `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=0.0085` `assist_rate=0.0664` `provider_weight=0.0106`	-

Team totals 0 0.92 13 6.7

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Jiří Letáček	G	4.4m	10.9%	Market-value substitute prior
Zaid Romero	D	13.7m	21.9%	Market-value substitute prior
Dani Carvajal	D	13.6m	30.0%	Market-value substitute prior
Orel Mangala	M	22.2m	31.2%	Market-value substitute prior
Mauro Arambarri	M	22.2m	51.0%	Market-value substitute prior
Christantus Uche	F	25.8m	58.1%	Market-value substitute prior

Rayo Vallecano — projected line vs season baseline (4-3-3)

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

Álvaro García F 81 0 0.19 0.15 ok 2 1.0 6.7 53.9 34 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9977, quality 0.437)	`market_value_eur=1500000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=39` `history_shrink=0.1136`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0108)	`blend_weight=0.0108` `history_matches=39` `season_overlap_discount=1.0` `per90_to_match_factor=0.8948` `prior_reliability=0.1467` `competition=La Liga`	totalShots: 1.825 -> 1.8141 fouls: 0.5514 -> 0.5586
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Andrés García', 'matchup_zone': 'LW vs CB', 'duel_win_rate': 0.321, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8545, 'skill_edge': -0.039, 'height_edge': -0.06, 'attacker_skill': 0.4374, 'defender_skill': 0.524, 'attacker_role': 'LW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Andrés García', 'market_value': 7600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.524}], 'xg_override': 0.2051}	totalShots: 1.8225 -> 1.5573 shotOffTarget: 1.1818 -> 1.0098 onTargetScoringAttempt: 0.6407 -> 0.5475 goals: 0.2603 -> 0.2224 expectedGoals: 0.24 -> 0.2051 expectedGoalsOnTarget: 0.2227 -> 0.1903 bigChanceMissed: 0.157 -> 0.1342
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.2051 -> 0.1859
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 12 by projected rating, fifa_overall 81.0)	`match_squad_rank=12` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1696` `goal_rate=0.2224` `scorer_weight=0.1985`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.067` `assist_rate=0.2934` `provider_weight=0.0868`	-

Sergio Camello F 73 1 0.30 0.17 80% 2 1.4 7.2 47.3 28 FBref Prior F_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0012, quality 0.533)	`market_value_eur=10900000` `quality_factor=0.533` `boost_factor=1.0012` `reference_quality=0.505` `history_matches=29` `history_shrink=0.1471`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0134)	`blend_weight=0.0134` `history_matches=29` `season_overlap_discount=1.0` `per90_to_match_factor=0.8142` `prior_reliability=0.14` `competition=La Liga`	goals: 0.4648 -> 0.4741 totalCross: 0.2302 -> 0.2375 wasFouled: 1.7834 -> 1.7907 onTargetScoringAttempt: 0.9953 -> 1.0025 fouls: 1.216 -> 1.2101 wonTackle: 0.8087 -> 0.8031
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Andrés García, Johan Mojica', 'matchup_zone': 'Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle', 'duel_win_rate': 0.196, 'pressing_faced': 'LOW', 'numerical_situation': '1v2', 'xg_multiplier': 0.9934, 'skill_edge': 0.0235, 'height_edge': -0.028, 'attacker_skill': 0.533, 'defender_skill': 0.4807, 'attacker_role': 'ST', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Andrés García', 'market_value': 7600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.524}, {'player': 'Johan Mojica', 'market_value': 1400000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.4374}], 'xg_override': 0.3326}	totalShots: 2.3459 -> 2.3304 shotOffTarget: 1.3434 -> 1.3345 onTargetScoringAttempt: 1.0025 -> 0.9959
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.3326 -> 0.3014
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 1 by projected rating, fifa_overall 74.0)	`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=1` `goal_probability=0.2602` `goal_rate=0.471` `scorer_weight=0.3768`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0919` `assist_rate=0.1014` `provider_weight=0.1002`	-

Jorge de Frutos F 75 0 0.13 0.22 40% 2 1.3 6.8 61.5 32 XGBoost F_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost F_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 1.0009, quality 0.533)	`market_value_eur=10900000` `quality_factor=0.533` `boost_factor=1.0009` `reference_quality=0.505` `history_matches=41` `history_shrink=0.1087`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Andrés García', 'matchup_zone': 'RW vs CB', 'duel_win_rate': 0.384, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9471, 'skill_edge': 0.004, 'height_edge': -0.04, 'attacker_skill': 0.533, 'defender_skill': 0.524, 'attacker_role': 'RW', 'attacker_mv_price_index': 1.0, 'defender_adjusted_parts': [{'player': 'Andrés García', 'market_value': 7600000, 'role': 'CB', 'price_index': 0.75, 'adjusted_quality': 0.524}], 'xg_override': 0.1441}`	totalShots: 1.3582 -> 1.2864 shotOffTarget: 0.7923 -> 0.7504 onTargetScoringAttempt: 0.5659 -> 0.536 expectedGoalsOnTarget: 0.2431 -> 0.2302 bigChanceMissed: 0.1557 -> 0.1475 goals: 0.1532 -> 0.1451 expectedGoals: 0.1521 -> 0.1441
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1441 -> 0.1306
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 9 by projected rating, fifa_overall 81.0)	`match_squad_rank=9` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1224` `goal_rate=0.1451` `scorer_weight=0.1313`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0596` `assist_rate=0.093` `provider_weight=0.0769`	-

Unai López M 80 0 0.05 0.02 132% 1 0.5 7.1 50.7 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 0.9975, quality 0.437)	`market_value_eur=2600000` `quality_factor=0.4374` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=35` `history_shrink=0.125`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0146)	`blend_weight=0.0146` `history_matches=35` `season_overlap_discount=1.0` `per90_to_match_factor=0.8876` `prior_reliability=0.18` `competition=La Liga`	totalShots: 0.8993 -> 0.891 wonTackle: 1.2143 -> 1.2206
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` duel_context={'opponent_faced': 'Mario Martín', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.34, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.8822, 'skill_edge': -0.0481, 'height_edge': -0.032, 'attacker_skill': 0.4374, 'defender_skill': 0.5444, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Mario Martín', 'market_value': 10700000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5444}], 'xg_override': 0.0603}	aerialWon: 0.4412 -> 0.8 totalShots: 0.9 -> 0.794 shotOffTarget: 0.622 -> 0.5487 onTargetScoringAttempt: 0.278 -> 0.2453 expectedGoals: 0.0683 -> 0.0603 goals: 0.0674 -> 0.0595
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.0603 -> 0.0547
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 2 by projected rating, fifa_overall 76.0)	`match_squad_rank=2` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0532` `goal_rate=0.0595` `scorer_weight=0.0543`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1204` `assist_rate=0.1025` `provider_weight=0.1103`	-

Pedro Díaz M 81 0 0.11 0.05 120% 2 1.2 6.8 55.2 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 0.9977, quality 0.437)	`market_value_eur=2900000` `quality_factor=0.4374` `boost_factor=0.9977` `reference_quality=0.505` `history_matches=40` `history_shrink=0.1111`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0024)	`blend_weight=0.0024` `history_matches=40` `season_overlap_discount=1.0` `per90_to_match_factor=0.8968` `prior_reliability=0.0333` `competition=La Liga`	totalCross: 0.799 -> 0.8143
`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': 'Mario Martín', 'matchup_zone': 'Central Mid vs Central Mid — Box-to-Box Midfield Contest', 'duel_win_rate': 0.385, 'pressing_faced': 'LOW', 'numerical_situation': '1v1', 'xg_multiplier': 0.9487, 'skill_edge': -0.0469, 'height_edge': 0.012, 'attacker_skill': 0.4402, 'defender_skill': 0.5444, 'attacker_role': 'CM', 'attacker_mv_price_index': 0.9, 'defender_adjusted_parts': [{'player': 'Mario Martín', 'market_value': 10700000, 'role': 'CM', 'price_index': 0.9, 'adjusted_quality': 0.5444}], 'xg_override': 0.1225}	aerialWon: 0.153 -> 1.1 totalShots: 1.64 -> 1.5559 shotOffTarget: 1.1728 -> 1.1126 onTargetScoringAttempt: 0.4672 -> 0.4432 expectedGoals: 0.1291 -> 0.1225 goals: 0.1258 -> 0.1193
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.1225 -> 0.111
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 7 by projected rating, fifa_overall 75.0)	`match_squad_rank=7` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.1051` `goal_rate=0.1193` `scorer_weight=0.1089`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.077` `assist_rate=0.0906` `provider_weight=0.087`	-

Adrià Pedrosa D 85 0 0.02 0.01 95% 1 0.3 6.6 44.9 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 0.9973, quality 0.437)	`market_value_eur=2700000` `quality_factor=0.4374` `boost_factor=0.9973` `reference_quality=0.505` `history_matches=32` `history_shrink=0.1351`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0041)	`blend_weight=0.0041` `history_matches=32` `season_overlap_discount=1.0` `per90_to_match_factor=0.9452` `prior_reliability=0.0467` `competition=La Liga`	fouls: 1.4052 -> 1.4105
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Martín Satriano', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 15 by projected rating, fifa_overall 74.0)	`match_squad_rank=15` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0239` `goal_rate=0.1476` `scorer_weight=0.0302`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.1438` `assist_rate=0.1737` `provider_weight=0.1701`	-

Mujaid Sadick D 83 0 0.00 - n/a 0 0.0 6.8 28.0 7 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 0.9913, quality 0.458)	`market_value_eur=4700000` `quality_factor=0.4585` `boost_factor=0.9913` `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': 'Martín Satriano', 'matchup_zone': 'Shadow Striker vs CB + Mid Cover — Layered Defense'}`	-
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	-
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 10 by projected rating, fifa_overall 84.0)	`match_squad_rank=10` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `goal_rate=0.0` `scorer_weight=0.001`	-
`integer_assist_projection`	Team scoreline allocation: 1 projected assists distributed by provider weight (xA x creation x appearance; nobody assists his own goal)	`allocation_applied=true` `team_assists=1` `assists_allocated=0` `assist_probability=0.0028` `assist_rate=0.0` `provider_weight=0.0027`	-

Florian Lejeune D 90 0 0.07 0.06 ok 1 1.4 6.9 60.8 30 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9979, quality 0.437)	`market_value_eur=1700000` `quality_factor=0.4374` `boost_factor=0.9979` `reference_quality=0.505` `history_matches=43` `history_shrink=0.1042`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0135)	`blend_weight=0.0135` `history_matches=43` `season_overlap_discount=1.0` `per90_to_match_factor=1.0` `prior_reliability=0.2` `competition=La Liga`	interceptionWon: 1.1432 -> 1.1638 wonTackle: 0.9578 -> 0.9719 totalShots: 1.2005 -> 1.2069
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Martín Satriano', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	expected_goals: 0.075 -> 0.068
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 4 by projected rating, fifa_overall 79.0)	`match_squad_rank=4` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0657` `goal_rate=0.0653` `scorer_weight=0.0627`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0107` `assist_rate=0.0129` `provider_weight=0.0112`	-

Iván Balliu D 83 0 0.03 0.00 2957% 0 0.0 6.6 26.0 28 FBref Prior D_service

Step-by-step (10 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost D_service raw output over 7 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9959, quality 0.437)	`market_value_eur=1100000` `quality_factor=0.4374` `boost_factor=0.9959` `reference_quality=0.505` `history_matches=20` `history_shrink=0.2`	-
`fbref_prior_blend`	FBref 2026-27 prior blended (weight 0.0173)	`blend_weight=0.0173` `history_matches=20` `season_overlap_discount=1.0` `per90_to_match_factor=0.9274` `prior_reliability=0.1333` `competition=La Liga`	totalShots: 0.3121 -> 0.3067
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Martín Satriano', 'matchup_zone': 'Shape fallback'}`	-
`scoreline_reset`	Team scoreline allocation: goal/assist counters reset to 0; the team's 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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `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 74.0)	`match_squad_rank=16` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0259` `goal_rate=0.0` `scorer_weight=0.021`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.0124` `assist_rate=0.0` `provider_weight=0.01`	-

Emil Audero G 90 0 0.00 - n/a 0.0 7.0 28.7 7 XGBoost G_service

Step-by-step (9 steps)

Step	Description	Key params	Changes
`xgboost_raw`	XGBoost G_service raw output over 3 target models	-	-
`market_value_boost`	Market-value quality scaling (boost 0.9873, quality 0.437)	`market_value_eur=2700000` `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': 'Martín Satriano, Ramón Terrats', 'matchup_zone': 'Goalkeeper shot-stopping context', 'opponent_lambda': 0.9511}`	-
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `team_xa_to_xg_ratio=0.65`	shots_faced: 9.0 -> 8.8 expected_saves: 2.2 -> 2.16 high_pressure_saves: 0.76 -> 0.74
`rankings_attached`	Display-only provenance: no published number changes. Global ranking attached (match squad rank 3 by projected rating, fifa_overall 79.0)	`match_squad_rank=3` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 1 projected goals distributed by scorer weight (xG x finishing x appearance)	`team_goals=1` `allocation_applied=true` `goals_allocated=0` `goal_probability=0.0` `scorer_weight=0.0` `squad_weight_total=1.1378`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.7191`	-

Pathé Ismaël Ciss M 89 0 0.04 0.08 49% 1 0.5 6.9 62.0 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 0.9975, quality 0.437)	`market_value_eur=1600000` `quality_factor=0.4374` `boost_factor=0.9975` `reference_quality=0.505` `history_matches=36` `history_shrink=0.122`	-
`final_cap`	Stats clamped to historical constraints and shot-component identity	`stats_clamped=0` `shot_identity_applied=false`	-
`enriched_model_output`	Model output after duel-context enrichment (pre router post-processing)	`duel_context_applied=true` `duel_context={'opponent_faced': 'Mario Martín, Nemanja Gudelj, Ramón Terrats', 'matchup_zone': 'Central Mid vs Mid + CDM Pressing Trap'}`	-
`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 1.05 (squad xG sum 1.1585, xG scale 0.9063, xA scale 1.0070, team xA 0.68 = 0.65 x lambda)	`scoreline_reset=true` `team_lambda=1.05` `squad_xg_sum=1.1585` `squad_xa_sum=0.6777` `team_expected_assists=0.6825` `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 82.0)	`match_squad_rank=6` `squad_role=starter` `squad_rank_basis=projected_rating` `affects_projection=false` `ranking_source=sofascore_plus_fifa_csv_filled` `ranking_status=combined`	-
`integer_goal_projection`	Team scoreline allocation: 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=0.0515` `scorer_weight=0.0449`	-
`integer_assist_projection`	Team scoreline allocation: 1 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=0.033` `assist_rate=0.0458` `provider_weight=0.0386`	-

Team totals 1 1.05 14 6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Augusto Batalla	G	4.5m	13.4%	Market-value substitute prior
Andrei Rațiu	D	14.4m	23.4%	Market-value substitute prior
Abdul Mumin	D	13.6m	29.9%	Market-value substitute prior
Isi Palazón	M	22.0m	49.9%	Market-value substitute prior
Óscar Valentín	M	29.7m	43.5%	Market-value substitute prior
Alemão	F	25.4m	56.2%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Mario Martín vs Pedro Díaz will be the pivotal duel. Total antagonist xG — Home: 0.67, Away: 0.86. Home danger zone: Shadow Striker vs CB + Mid Cover — Layered Defense. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.2% / 49.8%, dominance ratio 0.53, key duel: Mario Martín vs Pedro Díaz

Martín Satriano xG 0.22Francho Serrano xG 0.07Ramón Terrats xG 0.19Unai López xG 0.06Pedro Díaz xG 0.12Álvaro García xG 0.21

Summary

Antagonist matchup analysis for Getafe vs Rayo Vallecano. Most likely scoreline: 0-1. Lambdas derived from 5 home and 5 away individual player duels. Head-to-head: Getafe 0W-6D-4L vs Rayo Vallecano over 10 meetings.

Tactical parity between 3-4-2-1 and 4-3-3. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Mario Martín vs Pedro Díaz will be the pivotal duel. Total antagonist xG — Home: 0.67, Away: 0.86. Home danger zone: Shadow Striker vs CB + Mid Cover — Layered Defense. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Generated 2026-10-18 13:37:42 UTC · Soccer prediction reporting