Soccer predictions: actual data vs predicted data

Slate 20261011 · 12 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
Rayo Vallecano vs Athletic Club LaLiga	0-1	Athletic Club	23.6% / 23.9% / 52.5%	53.3%	54.5%	0.63	1.08 / 1.73	-	pending
Alavés vs Atl. Madrid LaLiga	1-2	Atl. Madrid	11.8% / 15.1% / 73.1%	73.7%	61.4%	0.72	1.06 / 2.78	-	pending
Elche vs Celta LaLiga	0-1	Celta	34.5% / 30.1% / 35.4%	35.4%	42.7%	0.69	1.05 / 1.07	-	pending
Real Sociedad vs Deportivo LaLiga	1-0	Real Sociedad	53.5% / 26.4% / 20.1%	40.5%	43.0%	0.74	1.50 / 0.81	-	pending
Málaga vs Espanyol LaLiga	0-1	Espanyol	22.5% / 29.6% / 47.9%	32.9%	38.4%	0.62	0.77 / 1.26	-	pending
Hull vs Everton Premier League	0-1	Everton	22.7% / 24.3% / 53.0%	51.0%	52.3%	0.72	1.02 / 1.69	-	pending
Barcelona vs Getafe LaLiga	3-0	Barcelona	91.6% / 5.9% / 2.5%	83.5%	46.9%	0.77	3.94 / 0.65	-	pending
Liverpool vs Man City Premier League	1-2	Man City	28.9% / 20.9% / 50.1%	71.9%	70.3%	0.73	1.59 / 2.13	-	pending
Crystal Palace vs Forest Premier League	1-0	Crystal Palace	42.5% / 25.4% / 32.0%	52.4%	56.0%	0.7	1.50 / 1.27	-	pending
Real Betis vs Osasuna LaLiga	1-0	Real Betis	63.1% / 21.4% / 15.4%	52.3%	48.5%	0.77	1.93 / 0.83	-	pending
Racing Club vs Valencia LaLiga	1-0	Racing Club	43.1% / 26.5% / 30.4%	47.5%	52.0%	0.7	1.42 / 1.15	-	pending
Real Madrid vs Villarreal LaLiga	3-1	Real Madrid	77.9% / 11.8% / 10.3%	86.5%	71.9%	0.73	3.54 / 1.35	-	pending

Match detail

Rayo Vallecano vs Athletic Club

LaLiga · 20261011 · 4-3-3 vs 4-2-3-1

Predicted 0-1Winner: Athletic ClubConfidence 0.63λ home/away 1.08 / 1.73Most-likely P 10.3%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Rayo Vallecano vs Athletic Club. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-3-3 vs 4-2-3-1 (duel lambdas: Home 1.082, Away 1.730). Final calibrated Poisson lambdas: Home 1.082, Away 1.730 (most likely score 0-1).

Home Starters 10/11 XGBoost (5 FBref) Away Starters 9/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.08 / 1.73 Final λ (H/A) 1.08 / 1.73

FBref Team Priors: Rayo Vallecano (Gls/90: 1.3333333333333333, GA/90: 1.33 → E[λ]: 0.988) vs Athletic Club (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.985) | 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	Rayo Vallecano	Athletic Club
League position	12.00	10.00
Points per game	1.14	1.33
Attack index	1.27	0.81
Defense (concede) index	0.69	1.85
Form multiplier	0.99	1.01
Standing λ multiplier	0.95	1.18

Lambda decomposition (how the goal rates were built)

Stage	Rayo Vallecano λ	Athletic Club λ
FBref Squad Prior E[λ] (weight 0.228)	0.988	0.985
Pre-competitive-floor	1.082	1.730
Pre-calibration (Micro-duels)	1.082	1.730
Final λ	1.082	1.730

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

Scoreline distribution & markets

Top 5 scorelines	P
0-1	10.3%
1-1	11.3%
1-2	9.7%
0-2	9.0%
1-0	6.4%

Home win	23.6%
Draw	23.9%
Away win	52.5%
Over 2.5	53.3%
BTTS yes	54.5%

Pregame fair line — favorite Athletic Club (52.5%), fair total 2.81, fair spread -0.65

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.

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Augusto Batalla	G	75	0.00	-	n/a	0	0.0	6.9	54.2	24	FBref Prior G_service
Andrei Rațiu	D	90	0.00	0.05	100%	1	0.8	6.7	61.8	28	FBref Prior D_service
Mujaid Sadick	D	55	0.00	-	n/a	0	0.0	6.7	32.7	6	XGBoost D_service
Marash Kumbulla	D	90	0.02	0.01	127%	0	0.2	6.8	16.4	12	Prior D_service
Adrià Pedrosa	D	80	0.00	0.01	100%	1	0.3	6.7	46.5	28	FBref Prior D_service
Isi Palazón	M	40	0.07	0.12	39%	1	1.4	6.7	58.0	20	XGBoost M_service
Pedro Díaz	M	54	0.11	0.05	119%	1	1.2	6.7	57.0	30	FBref Prior M_service
Giorgi Tsitaishvili	M	50	0.13	0.10	ok	1	1.0	6.7	31.6	12	XGBoost M_service
Jorge de Frutos	F	75	0.24	0.22	ok	1	1.3	6.9	63.5	31	XGBoost F_service
Alemão	F	20	0.14	0.09	58%	1	0.7	6.6	45.3	29	XGBoost F_service
Sergio Camello	F	67	0.26	0.17	52%	2	1.4	7.1	49.0	27	FBref Prior F_service
Team totals			1.08			10			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Emil Audero	G	4.4m	10.9%	Market-value substitute prior
Jozhua Vertrouwd	D	13.6m	21.7%	Market-value substitute prior
Luiz Felipe	D	13.6m	29.9%	Market-value substitute prior
Unai López	M	22.0m	30.7%	Market-value substitute prior
Fran Pérez	M	22.0m	49.9%	Market-value substitute prior
Randy Nteka	F	36.1m	59.1%	Market-value substitute prior

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Unai Simón	G	90	0	0.00	-	n/a	0	0.0	7.6	61.4	28	FBref Prior G_service
Dani Vivian	D	90	0	0.03	0.02	ok	0	0.5	7.1	55.2	18	Prior D_service
Aymeric Laporte	D	80	0	0.00	0.08	100%	1	0.5	7.0	57.0	24	FBref Prior D_service
Aitor Paredes	D	75	0	0.00	0.02	100%	1	0.3	7.0	34.2	24	FBref Prior D_service
Jesús Areso	D	69	0	0.00	0.01	100%	0	0.1	6.6	39.1	27	FBref Prior D_service
Nico Williams	M	61	1	0.38	0.13	181%	2	1.7	7.0	59.3	25	FBref Prior M_service
Mikel Jauregizar	M	42	0	0.16	0.03	424%	1	0.7	6.8	59.3	26	FBref Prior M_service
Oihan Sancet	M	86	0	0.45	0.26	70%	3	1.8	6.9	61.7	23	FBref Prior M_service
Beñat Prados	M	90	0	0.15	-	n/a	2	0.0	7.1	-	6	Prior M_service
Peio Canales	M	55	0	0.12	0.03	277%	1	0.7	6.8	44.3	6	FBref Prior M_service
Gorka Guruzeta	F	44	0	0.34	0.25	35%	1	2.1	6.7	61.4	25	FBref Prior F_service
Team totals			1	1.73			12			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Alex Padilla	G	4.4m	10.9%	Market-value substitute prior
Hugo Rincón	D	15.5m	41.0%	Market-value substitute prior
Adama Boiro	D	17.7m	60.2%	Market-value substitute prior
Iñaki Williams	M	22.2m	31.1%	Market-value substitute prior
Robert Navarro	M	22.1m	50.6%	Market-value substitute prior
Álvaro Djaló	F	16.9m	72.0%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~53% possession expected (Isi Palazón vs Nico Williams). Total antagonist xG — Home: 0.96, Away: 1.20. Home danger zone: Right Wing vs Left Back — Flank Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Midfield — possession 46.7% / 53.3%, dominance ratio 0.38, key duel: Isi Palazón vs Nico Williams

Jorge de Frutos xG 0.24Sergio Camello xG 0.26Alemão xG 0.14Oihan Sancet xG 0.33Peio Canales xG 0.09Nico Williams xG 0.28

Summary

Antagonist matchup analysis for Rayo Vallecano vs Athletic Club. Most likely scoreline: 0-1. Lambdas derived from 6 home and 6 away individual player duels.

Tactical parity between 4-3-3 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~53% possession expected (Isi Palazón vs Nico Williams). Total antagonist xG — Home: 0.96, Away: 1.20. Home danger zone: Right Wing vs Left Back — Flank Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Alavés vs Atl. Madrid

LaLiga · 20261011 · 3-5-2 vs 3-5-2

Predicted 1-2Winner: Atl. MadridConfidence 0.72λ home/away 1.06 / 2.78Most-likely P 8.8%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Alavés vs Atl. Madrid. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 3-5-2 vs 3-5-2 (duel lambdas: Home 1.242, Away 2.597). Final calibrated Poisson lambdas: Home 1.061, Away 2.778 (most likely score 1-2).

Home Starters 11/11 XGBoost (0 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.24 / 2.60 Final λ (H/A) 1.06 / 2.78

FBref Team Priors: Deportivo Alavés (Gls/90: 1.6666666666666667, GA/90: 1.67 → E[λ]: 2.877) vs Atlético Madrid (Gls/90: 2.333333333333333, GA/90: 2.33 → E[λ]: 2.886) | Blend Weight: 0.228

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Alavés	Atl. Madrid
League position	6.00	2.00
Points per game	1.57	2.29
Attack index	1.27	1.39
Defense (concede) index	0.61	0.69
Form multiplier	0.96	1.04
Standing λ multiplier	0.89	0.99

Lambda decomposition (how the goal rates were built)

Stage	Alavés λ	Atl. Madrid λ
FBref Squad Prior E[λ] (weight 0.228)	2.877	2.886
Pre-mismatch	1.242	2.597
Pre-calibration (Micro-duels)	1.242	2.597
Final λ	1.061	2.778

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
1-2	8.8%
0-2	8.3%
1-3	8.2%
0-3	7.7%
1-1	6.4%

Home win	11.8%
Draw	15.1%
Away win	73.1%
Over 2.5	73.7%
BTTS yes	61.4%

Pregame fair line — favorite Atl. Madrid (73.1%), fair total 3.84, fair spread -1.72

Projected players vs season baseline

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

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Antonio Sivera	G	90	0	0.00	-	n/a		0.0	7.2	65.3	31	XGBoost G_service
Youssef Enriquez	D	25	0	0.00	0.02	100%	0	0.2	6.8	40.4	30	XGBoost D_service
Nahuel Tenaglia	D	84	0	0.00	0.04	100%	0	0.6	6.7	61.5	31	XGBoost D_service
Nicolás Valentini	D	59	0	0.00	0.00	100%	0	0.1	6.9	38.4	9	XGBoost D_service
Antonio Blanco	M	75	0	0.08	0.04	115%	1	1.1	6.9	64.0	31	XGBoost M_service
Miguel Rodríguez	M	8	0	0.11	-	n/a	0	0.0	6.7	11.0	12	XGBoost M_service
Pablo Ibáñez	M	83	0	0.14	0.08	69%	1	1.2	6.8	63.1	30	XGBoost M_service
Ángel Pérez	M	70	0	0.16	0.07	111%	1	1.0	6.9	61.8	30	XGBoost M_service
Carles Aleñá	M	21	0	0.08	0.05	45%	0	0.6	6.7	47.9	30	XGBoost M_service
Toni Martínez	F	58	0	0.20	0.34	42%	1	2.6	6.7	66.0	30	XGBoost F_service
Lucas Boyé	F	81	1	0.21	0.34	40%	1	2.0	6.9	61.4	26	XGBoost F_service
Team totals			1	1.06			5			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Grégoire Swiderski	G	4.4m	10.9%	Market-value substitute prior
Jonny Otto	D	13.6m	29.9%	Market-value substitute prior
Moussa Diarra	D	13.6m	29.9%	Market-value substitute prior
Ander Guevara	M	22.0m	49.9%	Market-value substitute prior
Abderrahman Rebbach	M	22.0m	49.9%	Market-value substitute prior
Aitor Mañas	F	25.3m	55.9%	Market-value substitute prior

Atl. Madrid — projected line vs season baseline (3-5-2)

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Jan Oblak	G	90	0	0.00	-	n/a	0	0.0	7.0	57.0	26	FBref Prior G_service
Cristian Romero	D	70	0	0.00	0.09	100%	1	0.9	7.1	59.8	17	FBref Prior D_service
Dávid Hancko	D	78	0	0.00	0.05	100%	1	0.7	6.8	53.6	26	FBref Prior D_service
Marc Pubill	D	67	0	0.00	0.04	100%	0	0.4	6.7	49.3	27	FBref Prior D_service
Pablo Barrios	M	74	0	0.24	0.03	588%	1	0.8	7.1	59.8	13	FBref Prior M_service
Morten Hjulmand	M	50	0	0.22	0.02	1211%	1	0.3	6.9	48.2	10	FBref Prior M_service
Giuliano Simeone	M	68	1	0.38	0.11	251%	2	0.9	6.9	59.7	28	FBref Prior M_service
Alex Baena	M	65	0	0.31	0.08	319%	2	1.4	7.0	61.9	34	FBref Prior M_service
Kang-in Lee	M	67	0	0.37	0.15	144%	2	2.1	7.0	54.0	14	XGBoost M_service
Julián Alvarez	F	28	1	0.66	0.11	500%	2	1.4	6.8	50.7	20	FBref Prior F_service
Ademola Lookman	F	66	0	0.39	0.23	64%	2	1.5	6.8	59.2	25	FBref Prior F_service
Team totals			2	2.78			16			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Juan Musso	G	4.4m	10.9%	Market-value substitute prior
Marcos Llorente	D	25.7m	49.0%	Market-value substitute prior
Robin Le Normand	D	14.3m	23.2%	Market-value substitute prior
Rodrigo Mendoza	M	13.6m	45.2%	Market-value substitute prior
Alejandro Grimaldo	M	22.7m	53.3%	Market-value substitute prior
Jonathan David	F	26.4m	60.8%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~54% possession expected (Antonio Blanco vs Pablo Barrios). Total antagonist xG — Home: 0.78, Away: 1.51. 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 46.1% / 53.9%, dominance ratio 0.38, key duel: Antonio Blanco vs Pablo Barrios

Miguel Rodríguez xG 0.10Antonio Blanco xG 0.07Ángel Pérez xG 0.15Giuliano Simeone xG 0.25Morten Hjulmand xG 0.15Pablo Barrios xG 0.16

Summary

Antagonist matchup analysis for Alavés vs Atl. Madrid. Most likely scoreline: 1-2. Lambdas derived from 6 home and 6 away individual player duels.

Tactical parity between 3-5-2 and 3-5-2. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~54% possession expected (Antonio Blanco vs Pablo Barrios). Total antagonist xG — Home: 0.78, Away: 1.51. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Elche vs Celta

LaLiga · 20261011 · 4-3-3 vs 3-4-3

Predicted 0-1Winner: CeltaConfidence 0.69λ home/away 1.05 / 1.07Most-likely P 12.7%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Elche vs Celta. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-3-3 vs 3-4-3 (duel lambdas: Home 0.874, Away 1.045). Final calibrated Poisson lambdas: Home 1.049, Away 1.066 (most likely score 0-1).

Home Starters 11/11 XGBoost (7 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.87 / 1.04 Final λ (H/A) 1.05 / 1.07

FBref Team Priors: Elche (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.2) vs Celta Vigo (Gls/90: 0.25, GA/90: 0.25 → E[λ]: 0.2) | Blend Weight: 0.228

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Elche	Celta
League position	18.00	14.00
Points per game	1.02	1.17
Attack index	1.07	0.86
Defense (concede) index	0.80	1.29
Form multiplier	0.99	1.01
Standing λ multiplier	0.94	1.04

Lambda decomposition (how the goal rates were built)

Stage	Elche λ	Celta λ
FBref Squad Prior E[λ] (weight 0.228)	0.200	0.200
Pre-competitive-floor	1.049	1.066
Pre-calibration (Micro-duels)	0.874	1.045
Final λ	1.049	1.066

Scoreline distribution & markets

Top 5 scorelines	P
0-1	12.7%
1-1	13.6%
1-0	12.5%
0-0	12.2%
1-2	7.2%

Home win	34.5%
Draw	30.1%
Away win	35.4%
Over 2.5	35.4%
BTTS yes	42.7%

Pregame fair line — favorite Celta (35.4%), fair total 2.12, fair spread -0.02

Projected players vs season baseline

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

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Thomas Lemar	M	71	0.07	0.06	ok	1	0.6	6.9	58.4	27	XGBoost M_service
Gonzalo Villar	M	81	0.05	0.02	213%	1	0.3	6.9	50.7	26	FBref Prior M_service
Roy Revivo	D	87	0.00	0.02	100%	0	0.1	6.7	37.6	7	XGBoost D_service
Pedro Bigas	D	81	0.02	0.02	ok	0	0.3	6.7	45.4	28	FBref Prior D_service
Víctor Chust	D	89	0.05	0.02	136%	1	0.3	6.8	60.5	29	FBref Prior D_service
Rubén Sánchez	D	77	0.02	0.01	194%	0	0.3	6.6	33.3	28	XGBoost D_service
Javi Morcillo	M	85	0.03	0.01	115%	1	0.2	6.7	36.8	18	FBref Prior M_service
Matías Dituro	G	90	0.00	-	n/a		0.0	6.9	52.2	31	FBref Prior G_service
Tete Morente	F	79	0.10	0.03	275%	1	0.6	6.7	52.7	30	FBref Prior F_service
Fernando Niño	F	75	0.40	0.29	38%	2	1.1	7.0	50.6	10	FBref Prior F_service
Germán Valera	F	83	0.10	0.04	157%	1	0.5	6.9	57.5	39	XGBoost F_service
Team totals			1.05			11			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Iñaki Peña	G	4.4m	11.0%	Market-value substitute prior
Kevin Lomónaco	D	13.8m	31.0%	Market-value substitute prior
Buba Sangaré	D	13.6m	21.8%	Market-value substitute prior
Martim Neto	M	24.8m	50.0%	Market-value substitute prior
Marc Aguado	M	22.0m	30.8%	Market-value substitute prior
Facundo Buonanotte	F	26.4m	53.4%	Market-value substitute prior

Celta — projected line vs season baseline (3-4-3)

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Hugo Álvarez	M	73	0	0.10	0.10	ok	1	0.5	6.9	55.1	32	FBref Prior M_service
Ferrán Jutglà	F	73	0	0.21	0.17	ok	2	1.1	6.8	57.2	28	FBref Prior F_service
Hugo González	F	65	1	0.30	0.07	303%	2	0.5	6.8	20.4	17	FBref Prior F_service
Sergio Carreira	M	90	0	0.09	0.04	112%	1	0.4	7.0	59.0	34	FBref Prior M_service
Ilaix Moriba	M	84	0	0.07	0.03	96%	1	0.4	6.9	61.4	29	FBref Prior M_service
Aleix Febas	M	85	0	0.08	0.04	116%	1	0.5	6.9	57.1	26	FBref Prior M_service
Javier Rueda	M	71	0	0.06	0.02	142%	1	0.3	6.8	48.7	33	XGBoost M_service
Marcos Alonso	D	86	0	0.05	0.08	35%	1	0.7	7.0	59.5	27	FBref Prior D_service
Yoel Lago	D	89	0	0.02	0.00	304%	0	0.1	6.9	39.3	26	FBref Prior D_service
Sebastián Cáceres	D	90	0	0.01	0.00	210%	1	0.2	6.8	23.8	6	XGBoost D_service
Ionuț Radu	G	90	0	0.00	-	n/a		0.0	7.0	62.6	31	FBref Prior G_service
Team totals			1	1.07			12			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Altay Bayındır	G	4.5m	11.3%	Market-value substitute prior
Javi Rodríguez	D	10.3m	32.7%	Market-value substitute prior
Abdoulaye Faye	D	13.6m	21.8%	Market-value substitute prior
Fer López	M	22.6m	52.9%	Market-value substitute prior
Miguel Román	M	34.9m	41.4%	Market-value substitute prior
Williot Swedberg	F	30.4m	44.5%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~52% possession expected (Thomas Lemar vs Ilaix Moriba). Total antagonist xG — Home: 0.66, Away: 0.80. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Shadow Striker vs Centre Back — Half-Space Threat.

Midfield — possession 48.2% / 51.8%, dominance ratio 0.44, key duel: Thomas Lemar vs Ilaix Moriba

Thomas Lemar xG 0.06Gonzalo Villar xG 0.05Germán Valera xG 0.09Hugo Álvarez xG 0.09Ilaix Moriba xG 0.06Sergio Carreira xG 0.08

Summary

Antagonist matchup analysis for Elche vs Celta. Most likely scoreline: 0-1. Lambdas derived from 5 home and 7 away individual player duels.

Tactical parity between 4-3-3 and 3-4-3. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~52% possession expected (Thomas Lemar vs Ilaix Moriba). Total antagonist xG — Home: 0.66, Away: 0.80. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Shadow Striker vs Centre Back — Half-Space Threat.

Real Sociedad vs Deportivo

LaLiga · 20261011 · 4-4-2 vs 4-2-3-1

Predicted 1-0Winner: Real SociedadConfidence 0.74λ home/away 1.50 / 0.81Most-likely P 14.9%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Real Sociedad vs Deportivo. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-4-2 vs 4-2-3-1 (duel lambdas: Home 1.467, Away 0.823). Final calibrated Poisson lambdas: Home 1.498, Away 0.805 (most likely score 1-0).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.47 / 0.82 Final λ (H/A) 1.50 / 0.81

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	Real Sociedad	Deportivo
League position	8.00	7.00
Points per game	1.40	1.40
Attack index	1.00	0.93
Defense (concede) index	0.87	1.15
Form multiplier	1.00	1.00
Standing λ multiplier	0.94	1.03

Lambda decomposition (how the goal rates were built)

Stage	Real Sociedad λ	Deportivo λ
Pre-competitive-floor	1.498	0.805
Pre-calibration (Micro-duels)	1.467	0.823
Final λ	1.498	0.805

Scoreline distribution & markets

Top 5 scorelines	P
1-0	14.9%
1-1	12.1%
2-0	11.2%
0-0	10.1%
2-1	9.0%

Home win	53.5%
Draw	26.4%
Away win	20.1%
Over 2.5	40.5%
BTTS yes	43.0%

Pregame fair line — favorite Real Sociedad (53.5%), fair total 2.30, fair spread 0.69

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.

Real Sociedad — projected line vs season baseline (4-4-2)

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Mikel Oyarzabal	F	79	1	0.28	0.31	ok	2	1.5	6.9	61.1	32	FBref Prior F_service
Luka Sučić	M	83	0	0.23	0.10	135%	2	1.3	7.0	56.6	31	FBref Prior M_service
Gonçalo Guedes	F	77	0	0.16	0.10	58%	2	1.5	6.9	56.8	29	FBref Prior F_service
Carlos Soler	M	86	0	0.14	0.09	57%	1	0.8	6.9	60.9	30	FBref Prior M_service
Yangel Herrera	M	74	0	0.06	0.01	406%	1	0.3	6.8	45.2	24	FBref Prior M_service
Ander Barrenetxea	F	67	0	0.18	0.06	193%	2	0.9	6.8	54.5	31	FBref Prior F_service
Sergio Gómez	D	85	0	0.02	0.02	ok	1	0.4	6.8	58.5	29	FBref Prior D_service
Jon Martin	D	90	0	0.08	0.06	41%	0	0.4	6.8	51.1	29	FBref Prior D_service
Mamadou Sarr	D	83	0	0.14	0.02	488%	0	0.1	6.6	18.1	18	FBref Prior D_service
Luken Beitia	D	90	0	0.09	0.02	500%	1	0.2	6.8	19.2	17	FBref Prior D_service
Álex Remiro	G	90	0	0.00	-	n/a		0.0	7.1	61.5	30	FBref Prior G_service
Team totals			1	1.50			13			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Unai Marrero	G	4.4m	10.9%	Market-value substitute prior
Jon Aramburu	D	14.1m	22.7%	Market-value substitute prior
Héctor Fort	D	14.0m	31.7%	Market-value substitute prior
Jon Gorrotxategi	M	19.1m	71.3%	Market-value substitute prior
Beñat Turrientes	M	20.5m	41.1%	Market-value substitute prior
Takefusa Kubo	F	18.9m	44.7%	Market-value substitute prior

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Bil Nsongo	F	70	0.13	0.06	115%	1	0.9	6.7	44.7	12	FBref Prior F_service
Yeremay Hernández	F	72	0.08	0.01	923%	1	0.1	6.7	41.7	11	FBref Prior F_service
Jonathan Asp Jensen	F	70	0.13	0.03	418%	2	0.8	6.7	34.7	17	FBref Prior F_service
Lorenzo Amatucci	M	89	0.03	-	n/a	0	0.0	7.0	42.2	10	FBref Prior M_service
Mario Soriano	M	82	0.05	0.03	58%	1	0.6	7.1	44.6	11	FBref Prior M_service
Giacomo Quagliata	D	90	0.05	0.02	128%	1	0.5	6.8	41.4	11	FBref Prior D_service
José María Giménez	D	82	0.10	0.04	131%	1	0.5	6.9	42.9	24	FBref Prior D_service
Lucas Noubi	D	90	0.00	-	n/a	1	0.0	6.8	30.5	11	FBref Prior D_service
Ximo Navarro	D	89	0.05	0.02	135%	1	0.4	6.8	34.8	11	FBref Prior D_service
Leo Román	G	90	0.00	-	n/a		0.0	7.1	62.0	32	FBref Prior G_service
Luismi Cruz	F	73	0.08	0.03	152%	1	0.4	6.8	44.2	19	XGBoost F_service
Team totals			0.81			12			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Álvaro Ferllo	G	4.4m	10.9%	Market-value substitute prior
Bright Ede	D	13.7m	30.6%	Market-value substitute prior
Adrià Altimira	D	13.6m	29.9%	Market-value substitute prior
Marc Casadó	M	22.6m	52.9%	Market-value substitute prior
Angeliño	M	22.0m	50.1%	Market-value substitute prior
Adama Traoré	F	25.4m	56.5%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Luka Sučić vs Lorenzo Amatucci will be the pivotal duel. Total antagonist xG — Home: 0.92, Away: 0.50. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.0% / 50.0%, dominance ratio 0.53, key duel: Luka Sučić vs Lorenzo Amatucci

Mikel Oyarzabal xG 0.24Ander Barrenetxea xG 0.16Gonçalo Guedes xG 0.14Yeremay Hernández xG 0.08Bil Nsongo xG 0.13Jonathan Asp Jensen xG 0.13

Summary

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

Tactical parity between 4-4-2 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Luka Sučić vs Lorenzo Amatucci will be the pivotal duel. Total antagonist xG — Home: 0.92, Away: 0.50. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Málaga vs Espanyol

LaLiga · 20261011 · 3-5-2 vs 3-5-2

Predicted 0-1Winner: EspanyolConfidence 0.62λ home/away 0.77 / 1.26Most-likely P 16.6%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Málaga vs Espanyol. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 3-5-2 vs 3-5-2 (duel lambdas: Home 0.765, Away 1.257). Final calibrated Poisson lambdas: Home 0.765, Away 1.257 (most likely score 0-1).

Home Starters 9/11 XGBoost (0 FBref) Away Starters 10/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.77 / 1.26 Final λ (H/A) 0.77 / 1.26

FBref Team Priors: Málaga CF (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.412) vs Espanyol (Gls/90: 1.6666666666666667, GA/90: 1.67 → E[λ]: 0.407) | 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	Málaga	Espanyol
League position	20.00	15.00
Points per game	0.43	1.00
Attack index	0.35	0.87
Defense (concede) index	0.87	1.39
Form multiplier	0.97	1.03
Standing λ multiplier	0.63	1.08

Lambda decomposition (how the goal rates were built)

Stage	Málaga λ	Espanyol λ
FBref Squad Prior E[λ] (weight 0.228)	0.412	0.407
Pre-competitive-floor	0.765	1.257
Pre-calibration (Micro-duels)	0.765	1.257
Final λ	0.765	1.257

Scoreline distribution & markets

Top 5 scorelines	P
0-1	16.6%
0-0	13.3%
1-1	12.8%
0-2	10.5%
1-0	10.0%

Home win	22.5%
Draw	29.6%
Away win	47.9%
Over 2.5	32.9%
BTTS yes	38.4%

Pregame fair line — favorite Espanyol (47.9%), fair total 2.02, fair spread -0.49

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.

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Alfonso Herrero	G	90	0.00	-	n/a		0.0	7.2	58.7	10	XGBoost G_service
Adam Aznou	D	90	0.01	0.00	287%	0	0.1	6.9	6.4	10	Prior D_service
Fernando Calero	D	90	0.01	0.03	65%	0	0.3	6.8	53.7	20	Prior D_service
Jose Salinas	D	60	0.00	0.01	100%	0	0.1	6.6	18.5	30	XGBoost D_service
Jens-Lys Cajuste	M	9	0.07	-	n/a	0	0.0	6.7	16.8	4	XGBoost M_service
David Larrubia	M	82	0.11	0.06	89%	2	1.4	6.8	50.8	17	XGBoost M_service
Pablo Martínez	M	61	0.06	0.05	ok	1	0.8	6.8	60.5	26	XGBoost M_service
Izan Merino	M	70	0.06	0.00	1116%	0	0.1	6.8	46.5	10	XGBoost M_service
Juan Cruz	M	36	0.06	0.01	550%	1	0.4	6.7	50.6	17	XGBoost M_service
Chupete	F	80	0.20	0.31	34%	2	1.6	6.7	51.1	10	XGBoost F_service
Adrián Niño	F	32	0.15	0.10	52%	2	1.2	6.6	46.0	6	XGBoost F_service
Team totals			0.77			8			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Carlos Lopez	G	4.4m	10.9%	Market-value substitute prior
Diego Murillo	D	13.6m	29.9%	Market-value substitute prior
Juan Berrocal	D	13.6m	29.9%	Market-value substitute prior
Dani Lorenzo	M	22.0m	49.9%	Market-value substitute prior
Joaquín Muñoz	M	22.0m	49.9%	Market-value substitute prior
Julen Lobete	F	25.3m	55.9%	Market-value substitute prior

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Marko Dmitrović	G	90	0	0.00	-	n/a	0	0.0	7.1	61.2	31	FBref Prior G_service
Omar El Hilali	D	88	0	0.00	-	n/a	1	0.0	6.8	60.7	29	FBref Prior D_service
Quilindschy Hartman	D	50	0	0.00	0.01	100%	0	0.1	6.7	30.7	24	FBref Prior D_service
Vanja Drkušić	D	38	0	0.00	-	n/a	0	0.0	6.7	13.4	10	FBref Prior D_service
Urko González	M	63	0	0.12	0.02	587%	1	0.4	6.7	62.1	30	FBref Prior M_service
Tyrhys Dolan	M	72	0	0.15	0.05	194%	1	0.7	6.8	55.1	39	FBref Prior M_service
Gabriel Moscardo	M	43	0	0.10	0.01	687%	1	0.2	6.7	26.6	10	FBref Prior M_service
Javi Puado	M	90	0	0.09	-	n/a	1	0.0	6.9	9.3	7	Prior M_service
Pol Lozano	M	16	0	0.10	0.02	346%	1	0.4	6.8	47.7	28	FBref Prior M_service
Roberto Fernández	F	88	1	0.49	0.28	74%	2	1.5	6.9	62.9	31	FBref Prior F_service
Bryan Zaragoza	F	34	0	0.14	0.14	ok	1	1.2	6.8	60.1	12	XGBoost F_service
Team totals			1	1.26			10			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Angel Fortuno	G	4.4m	10.9%	Market-value substitute prior
Clemens Riedel	D	13.6m	21.8%	Market-value substitute prior
Unai Núñez	D	13.6m	21.7%	Market-value substitute prior
Edu Expósito	M	22.1m	30.8%	Market-value substitute prior
Álex Calatrava	M	22.0m	30.8%	Market-value substitute prior
Marcos Fernández	F	18.5m	71.9%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Jens-Lys Cajuste vs Urko González will be the pivotal duel. Total antagonist xG — Home: 1.04, Away: 1.06. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.4% / 50.6%, dominance ratio 0.47, key duel: Jens-Lys Cajuste vs Urko González

Izan Merino xG 0.10Jens-Lys Cajuste xG 0.11Pablo Martínez xG 0.10Gabriel Moscardo xG 0.10Urko González xG 0.11Tyrhys Dolan xG 0.14

Summary

Antagonist matchup analysis for Málaga vs Espanyol. Most likely scoreline: 0-1. Lambdas derived from 6 home and 6 away individual player duels.

Tactical parity between 3-5-2 and 3-5-2. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Jens-Lys Cajuste vs Urko González will be the pivotal duel. Total antagonist xG — Home: 1.04, Away: 1.06. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Hull vs Everton

Premier League · 20261011 · 5-4-1 vs 4-2-3-1

Predicted 0-1Winner: EvertonConfidence 0.72λ home/away 1.02 / 1.69Most-likely P 11.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Hull vs Everton. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 5-4-1 vs 4-2-3-1 (duel lambdas: Home 1.106, Away 1.609). Final calibrated Poisson lambdas: Home 1.022, Away 1.693 (most likely score 0-1).

Home Starters 11/11 XGBoost (7 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.11 / 1.61 Final λ (H/A) 1.02 / 1.69

FBref Team Priors: Hull City (Gls/90: 1.5, GA/90: 1.5 → E[λ]: 1.552) vs Everton (Gls/90: 1.5, GA/90: 1.5 → E[λ]: 1.552) | Blend Weight: 0.192

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Hull	Everton
League position	8.00	7.00
Points per game	1.46	1.55
Attack index	1.02	0.90
Defense (concede) index	0.79	0.93
Form multiplier	0.99	1.00
Standing λ multiplier	0.91	0.93

Lambda decomposition (how the goal rates were built)

Stage	Hull λ	Everton λ
FBref Squad Prior E[λ] (weight 0.192)	1.552	1.552
Pre-mismatch	1.106	1.609
Pre-competitive-floor	1.073	1.778
Pre-calibration (Micro-duels)	1.106	1.609
Final λ	1.022	1.693

Scoreline distribution & markets

Top 5 scorelines	P
0-1	11.1%
1-1	11.5%
1-2	9.7%
0-2	9.5%
0-0	6.7%

Home win	22.7%
Draw	24.3%
Away win	53.0%
Over 2.5	51.0%
BTTS yes	52.3%

Pregame fair line — favorite Everton (53.0%), fair total 2.71, fair spread -0.67

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.

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Oli McBurnie	F	86	0.23	0.11	109%	2	0.9	6.9	30.6	11	XGBoost F_service
Sorba Thomas	F	74	0.13	0.03	398%	1	0.3	6.8	16.2	15	XGBoost F_service
Regan Slater	M	87	0.08	0.02	311%	1	0.4	6.8	31.2	11	FBref Prior M_service
Matt Crooks	M	74	0.05	-	n/a	1	0.0	6.7	22.6	9	FBref Prior M_service
Ryan Giles	D	90	0.00	0.00	62%	0	0.1	6.7	31.1	11	FBref Prior D_service
Nobel Mendy	D	72	0.05	0.03	56%	1	0.3	6.8	46.0	28	FBref Prior D_service
John Egan	D	88	0.01	0.00	166%	0	0.3	6.7	31.6	11	FBref Prior D_service
Semi Ajayi	D	87	0.11	0.06	80%	1	0.3	6.7	31.0	11	FBref Prior D_service
Lewie Coyle	D	78	0.03	0.01	159%	0	0.1	6.6	29.5	11	FBref Prior D_service
Konstantinos Tzolakis	G	90	0.00	-	n/a		0.0	7.0	33.6	11	XGBoost G_service
Mohamed Belloumi	F	79	0.16	0.07	140%	2	1.2	6.9	34.6	21	XGBoost F_service
Team totals			1.02			11			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Jack Butland	G	4.4m	10.9%	Market-value substitute prior
Charlie Hughes	D	13.9m	31.2%	Market-value substitute prior
Lucas Herrington	D	22.7m	60.8%	Market-value substitute prior
Christos Mouzakitis	M	23.0m	54.3%	Market-value substitute prior
Tim Iroegbunam	M	22.7m	53.1%	Market-value substitute prior
Robinio Vaz	F	26.0m	59.1%	Market-value substitute prior

Everton — 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
Thierno Barry	F	83	1	0.57	0.28	105%	3	1.2	6.8	53.2	30	FBref Prior F_service
Jack Grealish	F	86	0	0.10	0.01	1001%	1	0.4	6.8	35.5	22	FBref Prior F_service
Kiernan Dewsbury-Hall	M	89	0	0.28	0.14	104%	3	1.5	7.2	55.4	27	FBref Prior M_service
Brennan Johnson	F	74	0	0.25	0.11	137%	2	0.8	6.7	51.4	33	FBref Prior F_service
Harrison Armstrong	M	84	0	0.12	0.04	235%	1	0.3	6.8	37.8	28	FBref Prior M_service
James Garner	M	86	0	0.07	0.03	162%	1	0.6	7.1	57.5	30	FBref Prior M_service
Jarrad Branthwaite	D	89	0	0.04	0.02	84%	1	0.4	6.9	50.3	21	FBref Prior D_service
James Tarkowski	D	90	0	0.07	0.07	ok	1	0.7	7.0	56.9	29	FBref Prior D_service
Ainsley Maitland-Niles	D	86	0	0.02	0.01	161%	1	0.3	6.6	29.5	10	XGBoost D_service
Jordan Pickford	G	90	0	0.00	-	n/a		0.0	7.1	56.1	30	FBref Prior G_service
Vitaliy Mykolenko	D	90	0	0.01	0.01	ok	0	0.2	6.8	51.0	29	FBref Prior D_service
Team totals			1	1.69			15			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Mark Travers	G	4.4m	10.9%	Market-value substitute prior
Jake O'Brien	D	14.2m	32.7%	Market-value substitute prior
Nathan Patterson	D	13.9m	31.6%	Market-value substitute prior
Hayden Hackney	M	26.4m	52.5%	Market-value substitute prior
Merlin Röhl	M	22.5m	31.8%	Market-value substitute prior
Tyrique George	F	26.1m	35.0%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~54% possession expected (Regan Slater vs James Garner). Total antagonist xG — Home: 0.66, Away: 0.94. 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 46.4% / 53.6%, dominance ratio 0.37, key duel: Regan Slater vs James Garner

Sorba Thomas xG 0.13Oli McBurnie xG 0.23Mohamed Belloumi xG 0.16Kiernan Dewsbury-Hall xG 0.22Thierno Barry xG 0.45Jack Grealish xG 0.08

Summary

Antagonist matchup analysis for Hull vs Everton. Most likely scoreline: 0-1. Lambdas derived from 7 home and 4 away individual player duels.

Tactical parity between 5-4-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~54% possession expected (Regan Slater vs James Garner). Total antagonist xG — Home: 0.66, Away: 0.94. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Barcelona vs Getafe

LaLiga · 20261011 · 3-5-2 vs 3-4-2-1

Predicted 3-0Winner: BarcelonaConfidence 0.77λ home/away 3.94 / 0.65Most-likely P 10.4%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Barcelona vs Getafe. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 3-5-2 vs 3-4-2-1 (duel lambdas: Home 3.784, Away 0.806). Final calibrated Poisson lambdas: Home 3.944, Away 0.650 (most likely score 3-0).

Home Starters 11/11 XGBoost (0 FBref) Away Starters 10/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 3.78 / 0.81 Final λ (H/A) 3.94 / 0.65

FBref Team Priors: FC Barcelona (Gls/90: 3.6666666666666665, GA/90: 4.0 → E[λ]: 0.896) vs Getafe (Gls/90: 0.3333333333333333, GA/90: 0.33 → E[λ]: 0.988) | 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	Barcelona	Getafe
League position	1.00	11.00
Points per game	3.00	1.14
Attack index	3.58	0.35
Defense (concede) index	0.61	0.81
Form multiplier	1.06	0.94
Standing λ multiplier	1.39	0.63

Lambda decomposition (how the goal rates were built)

Stage	Barcelona λ	Getafe λ
FBref Squad Prior E[λ] (weight 0.228)	0.896	0.988
Pre-mismatch	3.784	0.806
Pre-calibration (Micro-duels)	3.784	0.806
Final λ	3.944	0.650

Scoreline distribution & markets

Top 5 scorelines	P
3-0	10.4%
4-0	10.3%
5-0	8.1%
2-0	7.9%
3-1	6.8%

Home win	91.6%
Draw	5.9%
Away win	2.5%
Over 2.5	83.5%
BTTS yes	46.9%

Pregame fair line — favorite Barcelona (91.6%), fair total 4.59, fair spread 3.29

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.

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Joan García	G	82	0	0.00	-	n/a		0.0	7.0	62.7	29	XGBoost G_service
Pau Cubarsí	D	84	0	0.00	0.02	100%	1	0.2	7.1	53.7	30	XGBoost D_service
Jules Koundé	D	43	0	0.00	0.08	100%	1	0.4	6.8	50.4	25	XGBoost D_service
Alejandro Balde	D	12	0	0.00	0.01	100%	0	0.1	6.8	36.0	26	XGBoost D_service
Lamine Yamal	M	83	1	0.61	0.51	ok	4	3.7	7.1	67.7	29	XGBoost M_service
Pedri	M	72	0	0.28	0.05	502%	1	0.6	7.1	64.9	26	XGBoost M_service
Fermín López	M	74	0	0.36	0.27	35%	2	1.9	7.0	63.9	28	XGBoost M_service
Raphinha	M	79	1	0.55	0.57	ok	3	2.3	7.1	60.3	24	XGBoost M_service
Dani Olmo	M	37	0	0.35	0.18	100%	2	1.7	7.2	65.7	30	XGBoost M_service
Anthony Gordon	F	66	1	0.84	0.26	218%	3	1.6	6.8	52.9	27	XGBoost F_service
Karim Adeyemi	F	35	0	0.82	0.43	89%	3	1.5	6.9	58.5	11	XGBoost F_service
Team totals			3	3.94			21			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Dominik Livaković	G	4.5m	11.1%	Market-value substitute prior
Eric García	D	14.9m	36.0%	Market-value substitute prior
Gerard Martín	D	14.7m	35.2%	Market-value substitute prior
Rodri	M	23.5m	56.8%	Market-value substitute prior
Frenkie de Jong	M	23.1m	55.2%	Market-value substitute prior
Gabriel Jesus	F	26.0m	58.9%	Market-value substitute prior

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
David Soria	G	90	0.00	-	n/a	0	0.0	7.2	68.3	31	FBref Prior G_service
Andrés García	D	79	0.00	0.01	100%	0	0.4	6.7	45.2	21	FBref Prior D_service
Abdel Abqar	D	46	0.00	0.01	100%	0	0.1	6.6	51.2	18	FBref Prior D_service
Zaid Romero	D	86	0.00	0.04	100%	0	0.5	6.7	63.3	24	FBref Prior D_service
Mario Martín	M	83	0.06	0.08	ok	1	0.7	6.8	59.8	26	FBref Prior M_service
Orel Mangala	M	79	0.04	0.02	142%	0	0.3	6.7	51.1	9	FBref Prior M_service
Ramón Terrats	M	89	0.09	0.07	ok	2	1.0	7.1	60.8	29	FBref Prior M_service
Francho Serrano	M	70	0.04	0.01	250%	1	0.3	6.8	44.3	9	FBref Prior M_service
Christantus Uche	F	90	0.12	0.01	834%	2	0.2	7.0	29.8	13	Prior F_service
Martín Satriano	F	78	0.12	0.17	ok	1	1.7	6.8	63.1	31	FBref Prior F_service
Enes Ünal	F	77	0.12	0.09	ok	1	0.8	6.7	48.0	27	FBref Prior F_service
Team totals			0.65			9			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Jiří Letáček	G	4.4m	10.9%	Market-value substitute prior
Djené	D	13.6m	21.7%	Market-value substitute prior
Sebastián Boselli	D	10.5m	60.2%	Market-value substitute prior
Nemanja Gudelj	M	18.1m	69.2%	Market-value substitute prior
Oscar Lopez	M	22.0m	49.9%	Market-value substitute prior
Borja Mayoral	F	13.1m	72.2%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~54% possession expected (Lamine Yamal vs Mario Martín). Total antagonist xG — Home: 2.26, Away: 1.11. 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 54.5% / 45.5%, dominance ratio 0.65, key duel: Lamine Yamal vs Mario Martín

Raphinha xG 0.36Lamine Yamal xG 0.40Pedri xG 0.18Ramón Terrats xG 0.17Mario Martín xG 0.12Orel Mangala xG 0.08

Summary

Antagonist matchup analysis for Barcelona vs Getafe. Most likely scoreline: 3-0. Lambdas derived from 6 home and 7 away individual player duels.

Tactical parity between 3-5-2 and 3-4-2-1. Match outcome driven primarily by individual player quality. Home midfield dominates with ~54% possession expected (Lamine Yamal vs Mario Martín). Total antagonist xG — Home: 2.26, Away: 1.11. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Liverpool vs Man City

Premier League · 20261011 · 4-2-3-1 vs 4-2-3-1

Predicted 1-2Winner: Man CityConfidence 0.73λ home/away 1.59 / 2.13Most-likely P 8.7%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Liverpool vs Man City. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-2-3-1 (duel lambdas: Home 1.617, Away 2.100). Final calibrated Poisson lambdas: Home 1.594, Away 2.130 (most likely score 1-2).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (11 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.62 / 2.10 Final λ (H/A) 1.59 / 2.13

FBref Team Priors: Liverpool FC (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 3.5) vs Manchester City (Gls/90: 3.0, GA/90: 3.0 → E[λ]: 3.5) | Blend Weight: 0.192

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Liverpool	Man City
League position	7.00	1.00
Points per game	1.55	2.09
Attack index	1.05	1.17
Defense (concede) index	0.86	0.92
Form multiplier	0.97	1.03
Standing λ multiplier	0.96	1.04

Lambda decomposition (how the goal rates were built)

Stage	Liverpool λ	Man City λ
FBref Squad Prior E[λ] (weight 0.192)	3.500	3.500
Pre-competitive-floor	1.594	2.130
Pre-calibration (Micro-duels)	1.617	2.100
Final λ	1.594	2.130

Scoreline distribution & markets

Top 5 scorelines	P
1-2	8.7%
1-1	8.2%
2-2	7.0%
2-1	6.5%
1-3	6.2%

Home win	28.9%
Draw	20.9%
Away win	50.1%
Over 2.5	71.9%
BTTS yes	70.3%

Pregame fair line — favorite Man City (50.1%), fair total 3.72, fair spread -0.54

Projected players vs season baseline

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

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Lewis Koumas	F	80	0	0.14	0.03	451%	1	0.2	6.7	11.8	11	FBref Prior F_service
Bradley Barcola	F	76	0	0.21	0.05	343%	2	0.4	6.7	29.8	11	XGBoost F_service
Florian Wirtz	M	82	0	0.24	0.18	32%	2	1.5	7.0	53.3	27	FBref Prior M_service
Víctor Muñoz	F	81	0	0.17	0.16	ok	1	2.0	6.9	56.4	31	FBref Prior F_service
Alexis Mac Allister	M	87	0	0.10	0.07	33%	1	1.0	7.0	54.9	31	FBref Prior M_service
Miloš Kerkez	D	84	0	0.05	0.02	151%	1	0.2	6.7	46.8	31	FBref Prior D_service
Jérémy Jacquet	D	86	0	0.00	-	n/a	0	0.0	7.1	35.1	11	FBref Prior D_service
Virgil van Dijk	D	90	0	0.11	0.10	ok	1	0.7	7.2	58.4	31	FBref Prior D_service
Ronald Araújo	D	79	0	0.03	0.03	ok	0	0.2	6.8	39.6	30	FBref Prior D_service
Alisson	G	90	0	0.00	-	n/a		0.0	7.1	51.7	24	FBref Prior G_service
Dominik Szoboszlai	M	89	1	0.20	0.14	49%	2	1.8	7.2	57.7	30	FBref Prior M_service
Team totals			1	1.59			16			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Giorgi Mamardashvili	G	5.5m	15.8%	Market-value substitute prior
Jeremie Frimpong	D	14.8m	35.6%	Market-value substitute prior
Curtis Jones	D	14.8m	35.3%	Market-value substitute prior
Ryan Gravenberch	M	23.8m	58.0%	Market-value substitute prior
Mohamed Salah	M	22.8m	53.5%	Market-value substitute prior
Alexander Isak	F	27.1m	64.0%	Market-value substitute prior

Man City — 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
Joško Gvardiol	D	84	0	0.08	0.07	ok	1	0.5	6.9	40.6	16	FBref Prior D_service
Marc Guéhi	D	90	0	0.16	0.15	ok	1	0.9	7.2	59.3	30	FBref Prior D_service
Rúben Dias	D	88	0	0.06	0.02	227%	1	0.2	7.1	40.2	23	FBref Prior D_service
Matheus Nunes	D	87	0	0.00	0.00	54%	0	0.1	7.0	49.2	31	FBref Prior D_service
Gianluigi Donnarumma	G	90	0	0.00	-	n/a		0.0	6.9	57.2	30	FBref Prior G_service
Enzo Fernández	M	87	0	0.20	0.17	ok	2	1.4	7.1	56.5	28	FBref Prior M_service
Elliot Anderson	M	85	0	0.07	0.04	79%	1	1.0	7.3	59.7	30	FBref Prior M_service
Rayan Cherki	M	75	0	0.28	0.12	139%	3	1.5	7.2	58.4	31	FBref Prior M_service
Antoine Semenyo	F	84	0	0.16	0.13	ok	2	1.3	7.2	50.5	40	FBref Prior F_service
Erling Haaland	F	89	2	0.79	0.47	67%	4	2.7	7.3	53.5	29	FBref Prior F_service
Iliman Ndiaye	F	87	0	0.13	0.12	ok	2	1.0	6.8	47.6	36	FBref Prior F_service
Team totals			2	2.13			20			7.1

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Gerónimo Rulli	G	4.5m	11.5%	Market-value substitute prior
Nico O'Reilly	D	15.3m	25.3%	Market-value substitute prior
Abdukodir Khusanov	D	15.1m	24.7%	Market-value substitute prior
Ayyoub Bouaddi	M	15.6m	72.8%	Market-value substitute prior
Phil Foden	M	23.7m	34.2%	Market-value substitute prior
Jérémy Doku	F	27.0m	63.7%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Florian Wirtz vs Elliot Anderson will be the pivotal duel. Total antagonist xG — Home: 0.90, Away: 1.27. Home danger zone: CDM vs CDM. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.9% / 50.1%, dominance ratio 0.50, key duel: Florian Wirtz vs Elliot Anderson

Dominik Szoboszlai xG 0.17Bradley Barcola xG 0.18Lewis Koumas xG 0.12Rayan Cherki xG 0.22Erling Haaland xG 0.61Antoine Semenyo xG 0.13

Summary

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

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Florian Wirtz vs Elliot Anderson will be the pivotal duel. Total antagonist xG — Home: 0.90, Away: 1.27. Home danger zone: CDM vs CDM. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Crystal Palace vs Forest

Premier League · 20261011 · 3-4-2-1 vs 3-4-2-1

Predicted 1-0Winner: Crystal PalaceConfidence 0.7λ home/away 1.50 / 1.27Most-likely P 9.3%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Crystal Palace vs Forest. 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 3-4-2-1 (duel lambdas: Home 1.502, Away 1.271). Final calibrated Poisson lambdas: Home 1.502, Away 1.271 (most likely score 1-0).

Home Starters 11/11 XGBoost (7 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.50 / 1.27 Final λ (H/A) 1.50 / 1.27

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	Crystal Palace	Forest
League position	15.00	13.00
Points per game	1.09	1.19
Attack index	1.02	0.82
Defense (concede) index	0.86	1.24
Form multiplier	0.99	1.00
Standing λ multiplier	0.95	1.01

Lambda decomposition (how the goal rates were built)

Stage	Crystal Palace λ	Forest λ
Pre-competitive-floor	1.502	1.271
Pre-calibration (Micro-duels)	1.502	1.271
Final λ	1.502	1.271

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

Scoreline distribution & markets

Top 5 scorelines	P
1-0	9.3%
1-1	12.0%
2-1	9.0%
0-1	7.8%
1-2	7.6%

Home win	42.5%
Draw	25.4%
Away win	32.0%
Over 2.5	52.4%
BTTS yes	56.0%

Pregame fair line — favorite Crystal Palace (42.5%), fair total 2.77, fair spread 0.23

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.

Crystal Palace — 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
Tyrick Mitchell	M	85	0	0.12	0.06	90%	1	0.6	6.8	55.3	31	FBref Prior M_service
Adam Wharton	M	86	0	0.09	0.03	241%	1	0.7	7.0	54.8	29	FBref Prior M_service
Quinten Timber	M	86	0	0.11	0.03	325%	1	0.6	6.9	23.4	9	XGBoost M_service
Anan Khalaili	M	87	0	0.12	0.08	48%	1	0.6	6.9	36.5	12	FBref Prior M_service
Jaydee Canvot	D	89	0	0.06	0.05	ok	0	0.2	6.8	44.2	29	FBref Prior D_service
Chris Richards	D	90	0	0.10	0.07	40%	1	0.4	6.8	51.0	28	FBref Prior D_service
Daichi Kamada	M	83	0	0.07	0.06	ok	1	0.5	6.8	53.5	28	FBref Prior M_service
Honest Ahanor	D	90	0	0.00	-	n/a	1	0.0	6.6	9.6	7	XGBoost D_service
Walter Benítez	G	90	0	0.00	-	n/a		0.0	7.0	7.3	31	FBref Prior G_service
Ismaïla Sarr	F	82	1	0.41	0.31	33%	2	1.4	6.7	52.3	22	XGBoost F_service
Jørgen Strand Larsen	F	74	0	0.32	0.10	206%	2	1.1	6.7	52.3	30	FBref Prior F_service
Team totals			1	1.50			12			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Dean Henderson	G	5.5m	15.4%	Market-value substitute prior
Chadi Riad	D	14.3m	23.2%	Market-value substitute prior
Axel Disasi	D	15.2m	61.4%	Market-value substitute prior
Óscar Mingueza	M	19.0m	70.7%	Market-value substitute prior
Romain Esse	M	22.4m	51.6%	Market-value substitute prior
Jean-Philippe Mateta	F	26.4m	35.6%	Market-value substitute prior

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Matz Sels	G	90	0.00	-	n/a		0.0	6.9	53.6	27	FBref Prior G_service
Liam Delap	F	80	0.22	0.14	59%	2	1.1	6.8	49.6	29	FBref Prior F_service
Morgan Gibbs-White	M	89	0.24	0.28	ok	2	1.8	7.1	60.8	34	FBref Prior M_service
Dan Ndoye	F	67	0.21	0.05	332%	2	0.5	6.8	27.9	31	FBref Prior F_service
Neco Williams	D	89	0.08	0.04	70%	1	1.1	6.8	57.6	34	FBref Prior D_service
James McAtee	M	83	0.11	0.02	526%	1	0.4	6.9	24.9	30	FBref Prior M_service
Xaver Schlager	M	89	0.05	0.02	212%	1	0.5	6.9	32.4	11	FBref Prior M_service
Daniel Muñoz	M	77	0.11	0.05	137%	1	0.7	6.8	48.8	28	FBref Prior M_service
Murillo	D	87	0.07	0.03	91%	1	0.4	6.9	51.3	23	FBref Prior D_service
Ousmane Diomande	D	85	0.06	0.01	337%	0	0.2	6.7	11.9	11	FBref Prior D_service
Jair	D	83	0.02	0.02	32%	0	0.2	6.8	38.2	21	XGBoost D_service
Team totals			1.27			12			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

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

Antagonist / tactical summary

Midfield is evenly contested — Adam Wharton vs Morgan Gibbs-White will be the pivotal duel. Total antagonist xG — Home: 1.05, Away: 0.88. Home danger zone: Shadow Striker vs Centre Back — Half-Space Threat. Away danger zone: Central Mid vs Central Mid — Box-to-Box Midfield Contest.

Midfield — possession 50.8% / 49.2%, dominance ratio 0.52, key duel: Adam Wharton vs Morgan Gibbs-White

Tyrick Mitchell xG 0.10Adam Wharton xG 0.08Anan Khalaili xG 0.10James McAtee xG 0.10Morgan Gibbs-White xG 0.23Daniel Muñoz xG 0.10

Summary

Antagonist matchup analysis for Crystal Palace vs Forest. Most likely scoreline: 1-0. Lambdas derived from 7 home and 6 away individual player duels.

Tactical parity between 3-4-2-1 and 3-4-2-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Adam Wharton vs Morgan Gibbs-White will be the pivotal duel. Total antagonist xG — Home: 1.05, Away: 0.88. Home danger zone: Shadow Striker vs Centre Back — Half-Space Threat. Away danger zone: Central Mid vs Central Mid — Box-to-Box Midfield Contest.

Real Betis vs Osasuna

LaLiga · 20261011 · 4-3-3 vs 4-2-3-1

Predicted 1-0Winner: Real BetisConfidence 0.77λ home/away 1.93 / 0.83Most-likely P 12.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Real Betis vs Osasuna. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-3-3 vs 4-2-3-1 (duel lambdas: Home 1.818, Away 0.925). Final calibrated Poisson lambdas: Home 1.934, Away 0.835 (most likely score 1-0).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.82 / 0.93 Final λ (H/A) 1.93 / 0.83

FBref Team Priors: Real Betis (Gls/90: 1.3333333333333333, GA/90: 1.33 → E[λ]: 0.988) vs Osasuna (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.985) | 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	Real Betis	Osasuna
League position	4.00	14.00
Points per game	1.87	1.25
Attack index	1.00	0.80
Defense (concede) index	1.03	0.93
Form multiplier	1.03	0.97
Standing λ multiplier	1.02	0.88

Lambda decomposition (how the goal rates were built)

Stage	Real Betis λ	Osasuna λ
FBref Squad Prior E[λ] (weight 0.228)	0.988	0.985
Pre-mismatch	1.870	0.898
Pre-competitive-floor	2.033	0.878
Pre-calibration (Micro-duels)	1.818	0.925
Final λ	1.934	0.835

Scoreline distribution & markets

Top 5 scorelines	P
1-0	12.1%
2-0	11.7%
1-1	10.2%
2-1	9.8%
3-0	7.6%

Home win	63.1%
Draw	21.4%
Away win	15.4%
Over 2.5	52.3%
BTTS yes	48.5%

Pregame fair line — favorite Real Betis (63.1%), fair total 2.77, fair spread 1.10

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.

Real Betis — 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
Abdessamad Ezzalzouli	F	81	1	0.48	0.24	101%	3	1.9	7.3	60.6	29	XGBoost F_service
Cucho Hernández	F	80	0	0.42	0.28	47%	2	2.0	6.8	60.0	25	XGBoost F_service
Antony	F	80	0	0.33	0.22	49%	5	2.9	7.0	59.7	38	FBref Prior F_service
Isco	M	66	0	0.16	0.11	46%	1	0.9	6.9	55.6	17	FBref Prior M_service
Marc Roca	M	84	0	0.05	0.02	120%	1	0.5	7.0	49.2	31	FBref Prior M_service
Fran García	D	88	0	0.02	0.02	ok	0	0.1	6.8	29.9	30	FBref Prior D_service
Natan	D	89	0	0.06	0.02	261%	0	0.2	6.9	50.0	30	FBref Prior D_service
Diego Llorente	D	80	0	0.02	0.01	110%	0	0.1	6.8	48.1	25	FBref Prior D_service
Héctor Bellerín	D	87	0	0.09	0.03	218%	1	0.3	6.7	51.7	26	FBref Prior D_service
Álvaro Valles	G	90	0	0.00	-	n/a		0.0	7.2	59.7	31	FBref Prior G_service
Pablo Fornals	M	81	0	0.10	0.06	64%	1	0.9	7.1	58.9	31	FBref Prior M_service
Team totals			1	1.93			16			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Diego Conde	G	4.4m	10.9%	Market-value substitute prior
Valentín Gómez	D	14.0m	22.5%	Market-value substitute prior
Angel Ortiz	D	13.8m	22.1%	Market-value substitute prior
Sergi Altimira	M	22.7m	53.2%	Market-value substitute prior
Nelson Deossa	M	19.9m	57.0%	Market-value substitute prior
Troy Parrott	F	22.8m	54.4%	Market-value substitute prior

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Iker Muñoz	M	83	0.04	0.01	170%	1	0.3	6.9	42.7	30	FBref Prior M_service
Abel Bretones	D	88	0.02	0.00	1632%	0	0.1	6.6	43.2	30	FBref Prior D_service
Unai Santos	D	85	0.02	0.00	315%	0	0.1	6.7	13.3	9	FBref Prior D_service
Alejandro Catena	D	89	0.02	0.03	39%	0	0.3	6.8	59.4	29	XGBoost D_service
Iñigo Arguibide	D	81	0.02	0.00	477%	0	0.1	6.6	18.6	31	FBref Prior D_service
Aitor Fernández	G	90	0.00	-	n/a		0.0	7.1	9.5	31	FBref Prior G_service
Jon Moncayola	M	81	0.04	0.05	ok	1	0.5	6.8	60.1	29	FBref Prior M_service
Rubén García	F	69	0.11	0.07	63%	1	0.8	6.7	57.0	39	FBref Prior F_service
Asier Osambela	D	84	0.02	0.01	47%	1	0.2	6.6	32.9	34	FBref Prior D_service
Moi Gómez	M	76	0.04	0.01	584%	1	0.1	7.0	42.9	29	FBref Prior M_service
Ante Budimir	F	86	0.38	0.46	ok	2	2.6	6.9	63.4	31	FBref Prior F_service
Team totals			0.83			9			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Sergio Herrera	G	4.4m	13.1%	Market-value substitute prior
Enzo Boyomo	D	35.0m	61.3%	Market-value substitute prior
Jorge Herrando	D	13.6m	21.7%	Market-value substitute prior
Aimar Oroz	M	14.9m	43.9%	Market-value substitute prior
Lucas Torró	M	18.1m	56.4%	Market-value substitute prior
Romain Del Castillo	F	25.5m	56.6%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Pablo Fornals vs Jon Moncayola will be the pivotal duel. Total antagonist xG — Home: 1.19, Away: 0.58. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.1% / 49.9%, dominance ratio 0.51, key duel: Pablo Fornals vs Jon Moncayola

Abdessamad Ezzalzouli xG 0.37Antony xG 0.26Cucho Hernández xG 0.32Moi Gómez xG 0.04Ante Budimir xG 0.37Rubén García xG 0.10

Summary

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

Tactical parity between 4-3-3 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Pablo Fornals vs Jon Moncayola will be the pivotal duel. Total antagonist xG — Home: 1.19, Away: 0.58. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Racing Club vs Valencia

LaLiga · 20261011 · 4-2-3-1 vs 4-4-2

Predicted 1-0Winner: Racing ClubConfidence 0.7λ home/away 1.42 / 1.15Most-likely P 10.7%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Racing Club vs Valencia. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-4-2 (duel lambdas: Home 1.464, Away 1.119). Final calibrated Poisson lambdas: Home 1.422, Away 1.151 (most likely score 1-0).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.46 / 1.12 Final λ (H/A) 1.42 / 1.15

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Racing Club	Valencia
League position	16.00	19.00
Points per game	1.17	0.94
Attack index	1.07	0.73
Defense (concede) index	1.03	1.44
Form multiplier	1.01	0.99
Standing λ multiplier	1.05	1.02

Lambda decomposition (how the goal rates were built)

Stage	Racing Club λ	Valencia λ
Pre-competitive-floor	1.422	1.151
Pre-calibration (Micro-duels)	1.464	1.119
Final λ	1.422	1.151

Scoreline distribution & markets

Top 5 scorelines	P
1-0	10.7%
1-1	12.6%
2-1	8.9%
0-1	8.7%
0-0	7.7%

Home win	43.1%
Draw	26.5%
Away win	30.4%
Over 2.5	47.5%
BTTS yes	52.0%

Pregame fair line — favorite Racing Club (43.1%), fair total 2.57, fair spread 0.27

Projected players vs season baseline

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

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Yassir Zabiri	F	78	1	0.52	0.32	61%	2	1.3	7.0	46.1	11	FBref Prior F_service
Iñigo Vicente	F	84	0	0.08	0.02	260%	1	0.4	7.1	46.7	20	FBref Prior F_service
Pablo García	F	74	0	0.20	0.06	224%	2	0.7	6.7	30.7	28	FBref Prior F_service
Sergio Canales	M	82	0	0.14	0.08	81%	1	1.2	6.8	41.8	11	FBref Prior M_service
Iván Martín	M	85	0	0.05	0.03	88%	1	0.4	7.0	55.3	31	FBref Prior M_service
Matteo Prati	M	81	0	0.04	-	n/a	0	0.0	6.8	29.4	9	FBref Prior M_service
Jorge Salinas	D	90	0	0.06	0.02	137%	0	0.2	6.7	41.9	11	FBref Prior D_service
Jeanuël Belocian	D	90	0	0.04	0.01	204%	0	0.2	6.8	24.5	8	XGBoost D_service
Pablo Ramón	D	88	0	0.01	0.00	341%	1	0.2	6.8	31.2	11	FBref Prior D_service
Alvaro Mantilla	D	85	0	0.02	0.02	51%	0	0.2	6.7	34.6	11	XGBoost D_service
Julen Agirrezabala	G	90	0	0.00	-	n/a		0.0	6.8	33.6	16	FBref Prior G_service
Team totals			1	1.42			10			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

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

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Pepelu	M	82	0.05	0.08	46%	1	0.5	6.9	51.6	37	XGBoost M_service
Aaron Mayol	M	88	0.07	0.01	844%	1	0.2	6.8	11.8	12	XGBoost M_service
José Luis Gayà	D	80	0.01	0.02	ok	0	0.3	6.7	53.8	28	FBref Prior D_service
Justin De Haas	D	81	0.01	0.00	248%	1	0.1	6.8	29.9	7	FBref Prior D_service
Mouctar Diakhaby	D	78	0.05	0.01	316%	0	0.2	6.7	38.1	8	FBref Prior D_service
Pablo Maffeo	D	81	0.02	0.01	71%	0	0.2	6.7	58.2	28	FBref Prior D_service
Stole Dimitrievski	G	90	0.00	-	n/a		0.0	6.9	62.6	30	FBref Prior G_service
Guido Rodríguez	M	84	0.08	0.04	83%	1	0.7	7.1	58.0	26	FBref Prior M_service
Javier Guerra	M	81	0.24	0.10	144%	2	1.1	6.9	57.8	33	FBref Prior M_service
Hugo Duro	F	71	0.35	0.18	90%	2	0.7	6.6	56.1	30	FBref Prior F_service
Ryunosuke Sato	M	73	0.10	0.03	295%	1	0.5	6.7	31.6	10	FBref Prior M_service
Team totals			1.15			12			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Kayne van Oevelen	G	4.4m	10.9%	Market-value substitute prior
Arnau Martínez	D	13.9m	22.5%	Market-value substitute prior
César Tárrega	D	13.9m	22.3%	Market-value substitute prior
Harvey Elliott	M	22.8m	53.5%	Market-value substitute prior
Filip Ugrinić	M	29.8m	43.8%	Market-value substitute prior
Diego López	F	25.6m	57.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Matteo Prati vs Javier Guerra will be the pivotal duel. Total antagonist xG — Home: 0.79, Away: 0.69. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 48.5% / 51.5%, dominance ratio 0.45, key duel: Matteo Prati vs Javier Guerra

Sergio Canales xG 0.11Yassir Zabiri xG 0.40Iñigo Vicente xG 0.06Hugo Duro xG 0.27Javier Guerra xG 0.19Ryunosuke Sato xG 0.08

Summary

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

4-2-3-1 creates structural superiority against 4-4-2. Home team should exploit wider spaces and numerical advantages in transition. Midfield is evenly contested — Matteo Prati vs Javier Guerra will be the pivotal duel. Total antagonist xG — Home: 0.79, Away: 0.69. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Real Madrid vs Villarreal

LaLiga · 20261011 · 3-4-2-1 vs 5-4-1

Predicted 3-1Winner: Real MadridConfidence 0.73λ home/away 3.54 / 1.35Most-likely P 7.5%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Real Madrid vs Villarreal. 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 5-4-1 (duel lambdas: Home 3.369, Away 1.517). Final calibrated Poisson lambdas: Home 3.538, Away 1.348 (most likely score 3-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 3.37 / 1.52 Final λ (H/A) 3.54 / 1.35

FBref Team Priors: Real Madrid (Gls/90: 3.0, GA/90: 3.33 → E[λ]: 2.956) vs Villarreal (Gls/90: 1.3333333333333333, GA/90: 1.33 → E[λ]: 3.289) | 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	Real Madrid	Villarreal
League position	4.00	9.00
Points per game	2.14	1.14
Attack index	2.08	1.13
Defense (concede) index	1.04	0.92
Form multiplier	1.05	0.95
Standing λ multiplier	1.39	1.01

Lambda decomposition (how the goal rates were built)

Stage	Real Madrid λ	Villarreal λ
FBref Squad Prior E[λ] (weight 0.228)	2.956	3.289
Pre-mismatch	3.369	1.517
Pre-calibration (Micro-duels)	3.369	1.517
Final λ	3.538	1.348

Scoreline distribution & markets

Top 5 scorelines	P
3-1	7.5%
4-1	6.7%
2-1	6.4%
3-0	5.6%
3-2	5.1%

Home win	77.9%
Draw	11.8%
Away win	10.3%
Over 2.5	86.5%
BTTS yes	71.9%

Pregame fair line — favorite Real Madrid (77.9%), fair total 4.89, fair spread 2.19

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.

Real Madrid — 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
Thibaut Courtois	G	90	0	0.00	-	n/a	0	0.0	7.2	63.7	24	FBref Prior G_service
Dean Huijsen	D	84	0	0.00	0.06	100%	1	0.5	6.9	60.0	25	FBref Prior D_service
Trent Alexander-Arnold	D	53	0	0.00	0.02	100%	1	0.4	6.8	51.5	24	FBref Prior D_service
Marc Cucurella	D	61	0	0.00	0.07	100%	0	0.3	6.7	58.2	26	FBref Prior D_service
Jude Bellingham	M	76	1	0.49	0.17	186%	2	1.6	7.1	66.8	24	FBref Prior M_service
Arda Güler	M	50	0	0.44	0.12	261%	2	1.2	7.2	67.4	25	FBref Prior M_service
Federico Valverde	M	81	0	0.22	0.08	179%	1	1.3	6.9	68.6	26	FBref Prior M_service
Aurélien Tchouaméni	M	59	0	0.25	0.07	277%	1	1.3	6.9	63.1	24	XGBoost M_service
Kylian Mbappé	F	90	1	1.00	0.71	41%	4	4.2	7.4	64.5	24	FBref Prior F_service
Vinícius Júnior	F	81	1	0.63	0.38	65%	3	2.7	6.9	69.5	35	FBref Prior F_service
Yan Diomande	F	41	0	0.31	0.05	532%	1	0.6	6.8	59.0	12	FBref Prior F_service
Team totals			3	3.54			17			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Andriy Lunin	G	4.8m	12.7%	Market-value substitute prior
Álvaro Carreras	D	15.1m	24.9%	Market-value substitute prior
Ibrahima Konaté	D	15.0m	24.7%	Market-value substitute prior
Eduardo Camavinga	M	17.2m	59.4%	Market-value substitute prior
Brahim Díaz	M	17.6m	52.6%	Market-value substitute prior
Rodrygo	F	26.8m	62.7%	Market-value substitute prior

Villarreal — 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
Luiz Júnior	G	90	0	0.00	-	n/a		0.0	6.4	39.9	32	XGBoost G_service
Renato Veiga	D	90	0	0.00	0.01	100%	1	0.2	7.1	59.4	30	FBref Prior D_service
Carlos Romero	D	77	0	0.00	0.06	100%	0	1.1	6.7	62.1	29	FBref Prior D_service
Santiago Mouriño	D	56	0	0.00	0.03	100%	1	0.4	6.8	54.8	30	FBref Prior D_service
Pau Navarro	D	86	0	0.00	0.00	100%	0	0.0	6.9	44.2	32	FBref Prior D_service
Logan Costa	D	83	0	0.07	0.00	1978%	1	0.1	6.7	12.6	16	FBref Prior D_service
Alberto Moleiro	M	59	0	0.26	0.13	106%	2	1.0	7.1	61.1	40	FBref Prior M_service
Pape Gueye	M	75	0	0.23	0.15	55%	1	1.3	7.1	62.0	29	FBref Prior M_service
Tajon Buchanan	M	54	0	0.15	0.08	86%	1	0.9	6.9	58.0	32	FBref Prior M_service
Ilias Akhomach	M	31	0	0.12	0.06	95%	1	0.9	7.0	52.6	26	FBref Prior M_service
Georges Mikautadze	F	60	1	0.44	0.41	ok	2	2.1	6.8	63.3	32	FBref Prior F_service
Team totals			1	1.35			10			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Péter Gulácsi	G	4.4m	10.9%	Market-value substitute prior
Alexander Freeman	D	13.9m	31.2%	Market-value substitute prior
Juan Foyth	D	13.8m	22.2%	Market-value substitute prior
Nathan-Dylan Saliba	M	22.3m	51.2%	Market-value substitute prior
Santi Comesaña	M	22.2m	31.2%	Market-value substitute prior
Tani Oluwaseyi	F	15.9m	72.3%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~52% possession expected (Jude Bellingham vs Alberto Moleiro). Total antagonist xG — Home: 1.76, Away: 1.13. 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 51.6% / 48.4%, dominance ratio 0.56, key duel: Jude Bellingham vs Alberto Moleiro

Federico Valverde xG 0.11Arda Güler xG 0.23Jude Bellingham xG 0.26Carlos Romero xG 0.08Logan Costa xG 0.05Tajon Buchanan xG 0.13

Summary

Antagonist matchup analysis for Real Madrid vs Villarreal. Most likely scoreline: 3-1. Lambdas derived from 7 home and 7 away individual player duels.

Tactical parity between 3-4-2-1 and 5-4-1. Match outcome driven primarily by individual player quality. Home midfield dominates with ~52% possession expected (Jude Bellingham vs Alberto Moleiro). Total antagonist xG — Home: 1.76, Away: 1.13. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Generated 2026-10-11 13:36:30 UTC · Soccer prediction reporting