Soccer predictions: actual data vs predicted data

Slate 20261010 · 10 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	1-0	Rayo Vallecano	44.4% / 27.8% / 27.8%	41.4%	46.8%	0.71	1.34 / 1.00	-	pending
Alavés vs Atlético Madrid LaLiga	1-2	Atlético Madrid	13.9% / 16.1% / 70.0%	74.3%	64.2%	0.79	1.16 / 2.71	-	pending
Sunderland vs Brighton Premier League	1-2	Brighton	33.8% / 24.9% / 41.3%	54.9%	58.1%	0.71	1.36 / 1.52	-	pending
Chelsea vs Bournemouth Premier League	2-1	Chelsea	51.2% / 22.8% / 26.1%	60.7%	60.9%	0.74	1.86 / 1.27	-	pending
Aston Villa vs Brentford Premier League	1-2	Brentford	35.8% / 24.9% / 39.4%	55.8%	58.9%	0.69	1.42 / 1.50	-	pending
Ipswich vs Fulham Premier League	1-0	Ipswich	39.5% / 25.9% / 34.5%	50.9%	55.1%	0.68	1.41 / 1.30	-	pending
Barcelona vs Getafe LaLiga	3-0	Barcelona	87.2% / 8.2% / 4.6%	83.8%	57.0%	0.85	3.74 / 0.88	-	pending
Arsenal vs Leeds Premier League	2-1	Arsenal	58.8% / 20.8% / 20.4%	63.5%	60.5%	0.76	2.11 / 1.17	-	pending
Man Utd vs Tottenham Premier League	1-0	Man Utd	45.1% / 25.4% / 29.5%	51.7%	55.0%	0.73	1.54 / 1.20	-	pending
Real Madrid vs Villarreal LaLiga	3-1	Real Madrid	69.2% / 14.3% / 16.6%	88.6%	79.8%	0.79	3.39 / 1.74	-	pending

Match detail

Rayo Vallecano vs Athletic Club

LaLiga · 20261010 · 4-3-3 vs 4-2-3-1

Predicted 1-0Winner: Rayo VallecanoConfidence 0.71λ home/away 1.34 / 1.00Most-likely P 12.8%

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 1.217, Away 1.031). Final calibrated Poisson lambdas: Home 1.339, Away 1.000 (most likely score 1-0).

Home Starters 11/11 XGBoost (6 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.22 / 1.03 Final λ (H/A) 1.34 / 1.00

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	1.25	1.36
Attack index	1.07	0.92
Defense (concede) index	0.89	1.25
Form multiplier	0.99	1.01
Standing λ multiplier	0.98	1.06

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	1.339	1.000
Pre-calibration (Micro-duels)	1.217	1.031
Final λ	1.339	1.000

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	12.8%
1-1	13.0%
0-0	9.8%
0-1	9.5%
2-1	8.6%

Home win	44.4%
Draw	27.8%
Away win	27.8%
Over 2.5	41.4%
BTTS yes	46.8%

Pregame fair line — favorite Rayo Vallecano (44.4%), fair total 2.34, fair spread 0.34

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 G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Emil Audero	G	90	0	0.00	-	n/a		0.0	7.0	33.5	6	XGBoost G_service
Andrei Rațiu	D	90	0	0.08	0.05	48%	1	0.8	6.8	61.8	28	FBref Prior D_service
Álvaro García	M	81	0	0.21	0.16	32%	2	1.1	6.8	55.5	33	FBref Prior M_service
Sergio Camello	F	73	1	0.35	0.17	101%	2	1.4	7.1	49.0	27	FBref Prior F_service
Pathé Ismaël Ciss	M	89	0	0.05	0.09	38%	1	0.5	6.9	64.3	28	XGBoost M_service
Isi Palazón	M	69	0	0.16	0.12	39%	2	1.4	6.8	58.0	20	XGBoost M_service
Unai López	M	80	0	0.06	0.02	164%	1	0.5	7.0	52.6	26	FBref Prior M_service
Adrià Pedrosa	D	85	0	0.03	0.01	129%	1	0.3	6.6	46.5	28	FBref Prior D_service
Mujaid Sadick	D	83	0	0.00	-	n/a	0	0.0	6.8	32.7	6	XGBoost D_service
Florian Lejeune	D	90	0	0.08	0.06	33%	1	1.4	6.8	62.9	29	FBref Prior D_service
Jorge de Frutos	F	75	0	0.14	0.22	37%	2	1.3	6.8	63.5	31	XGBoost F_service
Team totals			1	1.34			16			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
Abdul Mumin	D	13.6m	29.9%	Market-value substitute prior
Marash Kumbulla	D	13.6m	29.9%	Market-value substitute prior
Pedro Díaz	M	23.1m	69.2%	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

Athletic Club — 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
Yuri Berchiche	D	82	0.04	0.02	90%	1	1.0	7.1	60.5	24	FBref Prior D_service
Aymeric Laporte	D	87	0.07	0.08	ok	1	0.5	7.0	57.0	24	FBref Prior D_service
Yeray Álvarez	D	79	0.03	0.02	83%	1	0.2	6.7	42.9	17	FBref Prior D_service
Jesús Areso	D	79	0.01	0.01	81%	1	0.1	6.7	39.1	27	FBref Prior D_service
Unai Simón	G	90	0.00	-	n/a		0.0	7.0	61.4	28	FBref Prior G_service
Iñigo Ruiz de Galarreta	M	72	0.05	0.02	117%	1	0.6	7.1	59.6	27	FBref Prior M_service
Beñat Gerenabarrena	M	88	0.03	0.00	587%	0	0.1	6.8	41.1	8	FBref Prior M_service
Robert Navarro	M	74	0.18	0.13	40%	2	0.8	7.0	53.3	36	XGBoost M_service
Peio Canales	M	88	0.09	0.03	167%	1	0.7	6.9	44.3	6	FBref Prior M_service
Iñaki Williams	M	72	0.30	0.21	46%	3	1.6	6.7	55.6	32	FBref Prior M_service
Álex Berenguer	M	84	0.07	0.08	ok	1	1.1	6.9	54.4	28	FBref Prior M_service
Team totals			1.00			14			6.9

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
Dani Vivian	D	14.3m	33.0%	Market-value substitute prior
Aitor Paredes	D	13.8m	22.1%	Market-value substitute prior
Mikel Jauregizar	M	24.7m	52.3%	Market-value substitute prior
Oihan Sancet	M	22.9m	32.6%	Market-value substitute prior
Nico Williams	F	25.8m	62.0%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Isi Palazón vs Peio Canales will be the pivotal duel. Total antagonist xG — Home: 0.89, Away: 0.60. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Attacking Mid vs Single Holding Mid — Space Creator Duel.

Midfield — possession 48.9% / 51.1%, dominance ratio 0.46, key duel: Isi Palazón vs Peio Canales

Jorge de Frutos xG 0.13Sergio Camello xG 0.32Pathé Ismaël Ciss xG 0.05Robert Navarro xG 0.17Álex Berenguer xG 0.07Iñaki Williams xG 0.29

Summary

Antagonist matchup analysis for Rayo Vallecano vs Athletic Club. Most likely scoreline: 1-0. Lambdas derived from 6 home and 5 away individual player duels.

Tactical parity between 4-3-3 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Isi Palazón vs Peio Canales will be the pivotal duel. Total antagonist xG — Home: 0.89, Away: 0.60. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Attacking Mid vs Single Holding Mid — Space Creator Duel.

Alavés vs Atlético Madrid

LaLiga · 20261010 · 5-3-2 vs 4-2-3-1

Predicted 1-2Winner: Atlético MadridConfidence 0.79λ home/away 1.16 / 2.71Most-likely P 8.9%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Alavés vs Atlético Madrid. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 5-3-2 vs 4-2-3-1 (duel lambdas: Home 1.319, Away 2.557). Final calibrated Poisson lambdas: Home 1.163, Away 2.713 (most likely score 1-2).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.32 / 2.56 Final λ (H/A) 1.16 / 2.71

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	Atlético Madrid
League position	6.00	2.00
Points per game	1.48	1.87
Attack index	1.07	1.13
Defense (concede) index	0.83	0.89
Form multiplier	0.98	1.02
Standing λ multiplier	0.95	1.00

Lambda decomposition (how the goal rates were built)

Stage	Alavés λ	Atlético Madrid λ
FBref Squad Prior E[λ] (weight 0.228)	2.877	2.886
Pre-mismatch	1.319	2.557
Pre-calibration (Micro-duels)	1.319	2.557
Final λ	1.163	2.713

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	8.9%
1-3	8.0%
0-2	7.6%
0-3	6.9%
1-1	6.6%

Home win	13.9%
Draw	16.1%
Away win	70.0%
Over 2.5	74.3%
BTTS yes	64.2%

Pregame fair line — favorite Atlético Madrid (70.0%), fair total 3.88, fair spread -1.55

Projected players vs season baseline

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

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Antonio Sivera	G	90	0	0.00	-	n/a		0.0	7.1	65.3	30	FBref Prior G_service
Ángel Pérez	M	84	0	0.14	0.07	91%	1	0.9	6.9	61.7	29	FBref Prior M_service
Nahuel Tenaglia	D	85	0	0.05	0.04	ok	1	0.7	6.8	61.1	30	FBref Prior D_service
Mariano Díaz	F	67	0	0.22	0.07	220%	1	0.5	6.7	28.6	20	XGBoost F_service
Toni Martínez	F	79	1	0.31	0.36	ok	2	2.6	6.8	65.8	29	FBref Prior F_service
Denis Suárez	M	70	0	0.09	0.03	179%	1	0.3	6.9	54.0	26	FBref Prior M_service
Antonio Blanco	M	86	0	0.06	0.04	64%	1	1.1	6.8	63.9	30	FBref Prior M_service
Pablo Ibáñez	M	78	0	0.11	0.09	ok	1	1.2	6.8	62.8	29	FBref Prior M_service
Abderrahman Rebbach	F	78	0	0.06	0.04	58%	1	0.6	6.8	50.2	39	XGBoost F_service
Jonny Otto	D	87	0	0.02	0.01	95%	0	0.2	6.8	53.2	29	XGBoost D_service
Nicolás Valentini	D	90	0	0.01	0.00	87%	0	0.1	6.7	34.5	8	FBref Prior D_service
Team totals			1	1.16			10			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Grégoire Swiderski	G	4.4m	10.9%	Market-value substitute prior
Youssef Enriquez	D	13.6m	30.2%	Market-value substitute prior
Victor Parada	D	13.6m	30.1%	Market-value substitute prior
Carlos Vicente	M	22.2m	50.8%	Market-value substitute prior
Carles Aleñá	M	13.2m	69.2%	Market-value substitute prior
Lucas Boyé	F	25.4m	33.6%	Market-value substitute prior

Atlético Madrid — 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
Jonathan David	F	72	1	0.75	0.39	94%	3	1.7	7.2	38.5	6	XGBoost F_service
Ademola Lookman	F	70	1	0.54	0.23	132%	2	1.5	6.8	59.1	24	FBref Prior F_service
Giuliano Simeone	M	77	0	0.18	0.11	65%	1	0.9	6.9	59.1	27	FBref Prior M_service
Johnny Cardoso	M	77	0	0.05	0.01	438%	1	0.2	6.9	49.9	22	FBref Prior M_service
Marcos Llorente	D	82	0	0.04	0.03	ok	1	0.5	6.9	61.2	29	FBref Prior D_service
Alejandro Grimaldo	M	88	0	0.36	0.23	59%	2	1.2	7.1	50.5	15	XGBoost M_service
Dávid Hancko	D	88	0	0.10	0.04	119%	1	0.7	7.0	53.0	25	FBref Prior D_service
Cristian Romero	D	79	0	0.08	0.06	45%	1	0.9	7.1	58.5	16	FBref Prior D_service
Marc Pubill	D	78	0	0.09	0.04	122%	1	0.5	6.8	51.2	26	FBref Prior D_service
Jan Oblak	G	90	0	0.00	-	n/a		0.0	7.0	56.7	25	FBref Prior G_service
Alex Baena	F	73	0	0.33	0.08	318%	3	1.4	7.3	61.1	31	FBref Prior F_service
Team totals			2	2.71			19			7.0

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
Robin Le Normand	D	14.3m	23.2%	Market-value substitute prior
Nahuel Molina	D	14.1m	32.3%	Market-value substitute prior
Pablo Barrios	M	24.4m	46.9%	Market-value substitute prior
Morten Hjulmand	M	17.7m	46.6%	Market-value substitute prior
Julián Alvarez	F	25.9m	75.6%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~53% possession expected (Antonio Blanco vs Giuliano Simeone). Total antagonist xG — Home: 0.81, Away: 1.57. 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 47.4% / 52.6%, dominance ratio 0.42, key duel: Antonio Blanco vs Giuliano Simeone

Mariano Díaz xG 0.18Toni Martínez xG 0.25Abderrahman Rebbach xG 0.05Alejandro Grimaldo xG 0.26Jonathan David xG 0.54Ademola Lookman xG 0.39

Summary

Antagonist matchup analysis for Alavés vs Atlético Madrid. Most likely scoreline: 1-2. Lambdas derived from 8 home and 6 away individual player duels.

Tactical parity between 5-3-2 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~53% possession expected (Antonio Blanco vs Giuliano Simeone). Total antagonist xG — Home: 0.81, Away: 1.57. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Sunderland vs Brighton

Premier League · 20261010 · 4-2-3-1 vs 4-2-3-1

Predicted 1-2Winner: BrightonConfidence 0.71λ home/away 1.36 / 1.52Most-likely P 8.8%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Sunderland vs Brighton. 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 1.356, Away 1.524). Final calibrated Poisson lambdas: Home 1.356, Away 1.524 (most likely score 1-2).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.36 / 1.52 Final λ (H/A) 1.36 / 1.52

FBref Team Priors: Sunderland (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 2.414) vs Brighton & Hove Albion (Gls/90: 2.5, GA/90: 3.5 → E[λ]: 1.724) | 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	Sunderland	Brighton
League position	14.00	3.00
Points per game	1.09	1.64
Attack index	1.02	1.30
Defense (concede) index	0.86	1.19
Form multiplier	0.97	1.03
Standing λ multiplier	0.94	1.20

Lambda decomposition (how the goal rates were built)

Stage	Sunderland λ	Brighton λ
FBref Squad Prior E[λ] (weight 0.192)	2.414	1.724
Pre-competitive-floor	1.356	1.524
Pre-calibration (Micro-duels)	1.356	1.524
Final λ	1.356	1.524

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

Scoreline distribution & markets

Top 5 scorelines	P
1-2	8.8%
1-1	11.7%
0-1	8.5%
2-1	7.9%
1-0	7.5%

Home win	33.8%
Draw	24.9%
Away win	41.3%
Over 2.5	54.9%
BTTS yes	58.1%

Pregame fair line — favorite Brighton (41.3%), fair total 2.88, fair spread -0.17

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.

Sunderland — 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
Robin Roefs	G	90	0	0.00	-	n/a		0.0	7.0	54.0	27	FBref Prior G_service
Nordi Mukiele	D	88	0	0.15	0.07	111%	1	0.8	6.8	50.7	27	FBref Prior D_service
Kevin Danso	D	89	0	0.05	0.03	98%	1	0.4	6.8	37.6	25	FBref Prior D_service
Omar Alderete	D	78	0	0.04	0.02	89%	0	0.4	6.8	44.3	30	FBref Prior D_service
Reinildo Mandava	D	87	0	0.00	0.00	ok	0	0.0	6.7	48.3	22	FBref Prior D_service
Wilson Isidor	F	70	1	0.27	0.10	156%	2	0.6	6.7	38.1	28	FBref Prior F_service
Nilson Angulo	F	69	0	0.14	0.07	91%	1	0.5	6.7	42.2	28	FBref Prior F_service
Enzo Le Fée	M	89	0	0.25	0.17	45%	2	1.1	6.9	58.4	29	FBref Prior M_service
Thomas Meunier	D	82	0	0.07	0.04	62%	1	0.8	6.7	40.0	13	FBref Prior D_service
Noah Sadiki	M	83	0	0.10	0.06	64%	1	0.7	6.8	55.0	27	FBref Prior M_service
Granit Xhaka	M	90	0	0.04	0.02	90%	1	0.5	7.3	59.5	26	FBref Prior M_service
Team totals			1	1.36			15			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Anthony Patterson	G	4.6m	11.9%	Market-value substitute prior
Daniel Ballard	D	14.4m	23.4%	Market-value substitute prior
Lutsharel Geertruida	D	14.4m	33.7%	Market-value substitute prior
Habib Diarra	M	18.7m	71.8%	Market-value substitute prior
Chris Rigg	M	15.8m	71.1%	Market-value substitute prior
Brian Brobbey	F	26.7m	36.3%	Market-value substitute prior

Brighton — 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
Charalampos Kostoulas	F	81	1	0.32	0.11	193%	2	0.9	6.9	41.8	26	FBref Prior F_service
Maxim De Cuyper	D	80	0	0.17	0.11	63%	1	0.6	6.8	48.7	33	FBref Prior D_service
Malick Yalcouyé	M	80	0	0.18	0.15	ok	2	0.7	6.9	36.0	10	FBref Prior M_service
Diego Gómez	M	80	0	0.20	0.13	54%	2	1.3	6.9	54.2	25	FBref Prior M_service
Yasin Ayari	M	86	0	0.13	0.05	163%	1	0.7	6.8	48.0	23	FBref Prior M_service
Pascal Groß	M	90	1	0.21	0.11	93%	2	1.0	7.3	59.2	29	FBref Prior M_service
Olivier Boscagli	D	88	0	0.01	0.01	77%	1	0.2	7.0	35.1	30	FBref Prior D_service
Lewis Dunk	D	90	0	0.05	0.04	ok	1	0.6	7.3	52.7	26	FBref Prior D_service
Luka Vušković	D	88	0	0.10	0.05	118%	1	0.8	7.1	37.5	10	FBref Prior D_service
Ferdi Kadıoğlu	D	87	0	0.05	0.05	ok	1	0.8	6.8	55.9	28	XGBoost D_service
Bart Verbruggen	G	90	0	0.00	-	n/a		0.0	7.0	58.2	29	FBref Prior G_service
Team totals			2	1.52			16			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Tom McGill	G	4.4m	10.9%	Market-value substitute prior
Mats Wieffer	D	14.5m	23.6%	Market-value substitute prior
Pascal Struijk	D	14.4m	33.9%	Market-value substitute prior
Georginio Rutter	M	23.1m	33.0%	Market-value substitute prior
Brajan Gruda	M	23.1m	54.8%	Market-value substitute prior
Yankuba Minteh	F	26.7m	62.2%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Noah Sadiki vs Yasin Ayari will be the pivotal duel. Total antagonist xG — Home: 0.71, Away: 0.93. 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 50.2% / 49.8%, dominance ratio 0.51, key duel: Noah Sadiki vs Yasin Ayari

Granit Xhaka xG 0.04Wilson Isidor xG 0.24Nilson Angulo xG 0.12Pascal Groß xG 0.19Malick Yalcouyé xG 0.16Charalampos Kostoulas xG 0.28

Summary

Antagonist matchup analysis for Sunderland vs Brighton. Most likely scoreline: 1-2. Lambdas derived from 5 home and 5 away individual player duels.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Noah Sadiki vs Yasin Ayari will be the pivotal duel. Total antagonist xG — Home: 0.71, Away: 0.93. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Chelsea vs Bournemouth

Premier League · 20261010 · 3-4-2-1 vs 4-2-3-1

Predicted 2-1Winner: ChelseaConfidence 0.74λ home/away 1.86 / 1.27Most-likely P 9.6%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Chelsea vs Bournemouth. 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 4-2-3-1 (duel lambdas: Home 1.791, Away 1.348). Final calibrated Poisson lambdas: Home 1.865, Away 1.274 (most likely score 2-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.79 / 1.35 Final λ (H/A) 1.86 / 1.27

FBref Team Priors: Chelsea (Gls/90: 3.5, GA/90: 3.5 → E[λ]: 2.414) vs Bournemouth (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 2.414) | 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	Chelsea	Bournemouth
League position	10.00	17.00
Points per game	1.37	1.00
Attack index	1.19	0.90
Defense (concede) index	0.98	1.28
Form multiplier	1.02	0.98
Standing λ multiplier	1.07	1.06

Lambda decomposition (how the goal rates were built)

Stage	Chelsea λ	Bournemouth λ
FBref Squad Prior E[λ] (weight 0.192)	2.414	2.414
Pre-mismatch	1.791	1.348
Pre-competitive-floor	1.935	1.321
Pre-calibration (Micro-duels)	1.791	1.348
Final λ	1.865	1.274

Scoreline distribution & markets

Top 5 scorelines	P
2-1	9.6%
1-1	10.4%
1-0	8.0%
2-0	7.5%
1-2	6.6%

Home win	51.2%
Draw	22.8%
Away win	26.1%
Over 2.5	60.7%
BTTS yes	60.9%

Pregame fair line — favorite Chelsea (51.2%), fair total 3.14, fair spread 0.59

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.

Chelsea — 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
Pep Chavarría	D	89	0	0.03	0.01	161%	0	0.3	6.7	47.2	31	FBref Prior D_service
Moisés Caicedo	M	86	0	0.06	0.03	94%	1	0.6	7.0	55.5	24	FBref Prior M_service
Reece James	D	89	0	0.11	0.03	246%	2	0.8	7.0	48.3	26	FBref Prior D_service
Pedro Neto	F	82	0	0.21	0.08	142%	2	0.9	6.8	47.4	34	FBref Prior F_service
Levi Colwill	D	88	0	0.00	0.00	198%	0	0.1	6.8	35.3	13	FBref Prior D_service
Maxence Lacroix	D	87	0	0.09	0.07	37%	1	0.7	6.8	53.8	28	FBref Prior D_service
Cole Palmer	M	88	1	0.39	0.34	ok	3	2.5	7.1	61.0	31	FBref Prior M_service
Wesley Fofana	D	79	0	0.02	0.02	ok	0	0.2	6.8	49.4	26	FBref Prior D_service
Emiliano Martínez	G	90	0	0.00	-	n/a		0.0	7.1	57.5	26	FBref Prior G_service
Morgan Rogers	M	88	1	0.49	0.22	122%	3	2.4	7.2	59.5	32	FBref Prior M_service
Danny Welbeck	F	75	0	0.33	0.18	83%	2	1.0	6.7	50.4	29	FBref Prior F_service
Team totals			2	1.86			15			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Mike Penders	G	5.3m	15.0%	Market-value substitute prior
Trevoh Chalobah	D	15.0m	36.3%	Market-value substitute prior
Jorrel Hato	D	14.9m	24.5%	Market-value substitute prior
Valentín Barco	M	15.5m	72.1%	Market-value substitute prior
Marco Palestra	M	23.2m	55.6%	Market-value substitute prior
Estêvão	F	27.1m	63.9%	Market-value substitute prior

Bournemouth — 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
Đorđe Petrović	G	90	0	0.00	-	n/a		0.0	6.9	57.7	29	FBref Prior G_service
Evanilson	F	83	0	0.20	0.24	ok	2	1.6	6.7	54.7	29	FBref Prior F_service
Marcus Tavernier	F	85	1	0.25	0.24	ok	2	1.7	7.4	51.3	35	FBref Prior F_service
Ryan Christie	M	69	0	0.08	0.06	42%	1	0.8	6.8	50.0	24	FBref Prior M_service
Rayan	F	84	0	0.26	0.13	96%	2	1.5	6.9	48.9	35	FBref Prior F_service
Lewis Cook	M	84	0	0.02	-	n/a	1	0.0	6.8	46.7	19	FBref Prior M_service
Tyler Adams	M	80	0	0.02	0.00	412%	1	0.1	6.9	48.1	21	FBref Prior M_service
Adrien Truffert	D	90	0	0.05	0.04	ok	1	0.4	6.9	57.3	29	FBref Prior D_service
António Silva	D	90	0	0.18	0.08	114%	1	0.4	7.0	34.9	10	FBref Prior D_service
James Hill	D	90	0	0.02	0.03	ok	0	0.3	7.0	58.6	29	FBref Prior D_service
Adam Smith	D	84	0	0.00	0.00	231%	0	0.0	6.6	34.2	29	FBref Prior D_service
Team totals			1	1.27			15			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Michele Di Gregorio	G	4.7m	12.3%	Market-value substitute prior
Bafodé Diakité	D	14.4m	33.9%	Market-value substitute prior
Álex Jiménez	D	14.3m	33.3%	Market-value substitute prior
Alex Scott	M	23.5m	33.9%	Market-value substitute prior
Justin Kluivert	M	22.9m	32.6%	Market-value substitute prior
Eli Junior Kroupi	F	27.0m	63.7%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~53% possession expected (Morgan Rogers vs Tyler Adams). Total antagonist xG — Home: 0.97, Away: 0.80. Home danger zone: Central Mid vs Defensive Mid — Pressing/Creation Duel. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 53.2% / 46.8%, dominance ratio 0.61, key duel: Morgan Rogers vs Tyler Adams

Pedro Neto xG 0.13Danny Welbeck xG 0.22Cole Palmer xG 0.25Ryan Christie xG 0.08Rayan xG 0.26Evanilson xG 0.20

Summary

Antagonist matchup analysis for Chelsea vs Bournemouth. Most likely scoreline: 2-1. Lambdas derived from 5 home and 4 away individual player duels.

Tactical parity between 3-4-2-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Home midfield dominates with ~53% possession expected (Morgan Rogers vs Tyler Adams). Total antagonist xG — Home: 0.97, Away: 0.80. Home danger zone: Central Mid vs Defensive Mid — Pressing/Creation Duel. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Aston Villa vs Brentford

Premier League · 20261010 · 4-2-3-1 vs 4-2-3-1

Predicted 1-2Winner: BrentfordConfidence 0.69λ home/away 1.42 / 1.50Most-likely P 8.6%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Aston Villa vs Brentford. 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 1.289, Away 1.545). Final calibrated Poisson lambdas: Home 1.418, Away 1.499 (most likely score 1-2).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.29 / 1.54 Final λ (H/A) 1.42 / 1.50

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	Aston Villa	Brentford
League position	16.00	4.00
Points per game	1.09	1.55
Attack index	0.93	1.06
Defense (concede) index	0.82	1.15
Form multiplier	0.97	1.03
Standing λ multiplier	0.89	1.09

Lambda decomposition (how the goal rates were built)

Stage	Aston Villa λ	Brentford λ
Pre-competitive-floor	1.418	1.499
Pre-calibration (Micro-duels)	1.289	1.545
Final λ	1.418	1.499

Scoreline distribution & markets

Top 5 scorelines	P
1-2	8.6%
1-1	11.6%
2-1	8.2%
0-1	8.0%
1-0	7.6%

Home win	35.8%
Draw	24.9%
Away win	39.4%
Over 2.5	55.8%
BTTS yes	58.9%

Pregame fair line — favorite Brentford (39.4%), fair total 2.92, fair spread -0.08

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.

Aston Villa — 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
Nicolas Jackson	F	75	1	0.30	0.07	308%	3	0.9	6.8	31.0	9	FBref Prior F_service
Emiliano Buendía	F	79	0	0.14	0.09	51%	1	1.2	6.9	49.8	38	XGBoost F_service
Johan Manzambi	M	81	0	0.31	0.06	392%	3	0.6	6.8	20.4	7	XGBoost M_service
John McGinn	F	82	0	0.11	0.08	44%	1	0.6	6.8	46.0	31	FBref Prior F_service
João Gomes	M	83	0	0.05	0.03	93%	1	0.4	6.7	51.6	25	FBref Prior M_service
Boubacar Kamara	M	87	0	0.07	0.02	372%	1	0.2	6.9	40.5	12	FBref Prior M_service
Matteo Ruggeri	D	86	0	0.01	0.00	254%	0	0.1	6.7	39.4	29	FBref Prior D_service
Tyrone Mings	D	89	0	0.09	0.05	84%	1	0.4	6.9	37.3	25	FBref Prior D_service
Victor Lindelöf	D	86	0	0.08	0.03	214%	0	0.1	6.7	33.2	28	FBref Prior D_service
Aaron Wan-Bissaka	D	80	0	0.00	-	n/a	0	0.0	6.6	43.8	26	FBref Prior D_service
Zion Suzuki	G	90	0	0.00	-	n/a		0.0	7.0	28.5	10	FBref Prior G_service
Team totals			1	1.42			13			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Marco Bizot	G	4.4m	13.1%	Market-value substitute prior
Ian Maatsen	D	14.6m	23.8%	Market-value substitute prior
Taylor Harwood-Bellis	D	14.4m	33.7%	Market-value substitute prior
Amadou Onana	M	23.4m	56.1%	Market-value substitute prior
Douglas Luiz	M	22.7m	53.2%	Market-value substitute prior
Donyell Malen	F	26.8m	62.7%	Market-value substitute prior

Brentford — 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
Igor Thiago	F	89	1	0.45	0.49	ok	3	2.0	6.7	56.4	30	FBref Prior F_service
Kevin Schade	F	86	1	0.31	0.22	41%	3	1.4	7.0	50.8	38	FBref Prior F_service
Yehor Yarmoliuk	M	80	0	0.04	0.03	54%	1	0.3	6.9	55.9	29	FBref Prior M_service
Jaidon Anthony	F	80	0	0.19	0.13	47%	2	1.2	6.8	49.8	37	FBref Prior F_service
Vitaly Janelt	M	86	0	0.04	0.05	ok	1	0.5	7.0	53.3	23	FBref Prior M_service
Mamadou Sangare	M	79	0	0.07	0.04	65%	1	0.6	6.9	34.9	10	FBref Prior M_service
Kristoffer Ajer	D	88	0	0.01	0.01	147%	0	0.1	6.7	46.1	29	FBref Prior D_service
Jannik Schuster	D	90	0	0.03	0.01	164%	1	0.1	6.9	22.7	10	FBref Prior D_service
Michael Kayode	D	80	0	0.08	0.05	46%	1	0.3	6.7	56.8	29	FBref Prior D_service
Caoimhin Kelleher	G	90	0	0.00	-	n/a		0.0	7.0	58.2	29	FBref Prior G_service
Keane Lewis-Potter	D	83	0	0.15	0.11	40%	1	1.0	6.7	55.6	30	FBref Prior D_service
Team totals			2	1.50			16			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Hákon Rafn Valdimarsson	G	4.4m	10.9%	Market-value substitute prior
Sepp van den Berg	D	14.8m	35.3%	Market-value substitute prior
Nathan Collins	D	14.7m	23.9%	Market-value substitute prior
Mikkel Damsgaard	M	18.6m	52.2%	Market-value substitute prior
Antoni Milambo	M	22.6m	52.5%	Market-value substitute prior
Dango Ouattara	F	28.4m	55.2%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Johan Manzambi vs Mamadou Sangare will be the pivotal duel. Total antagonist xG — Home: 0.87, Away: 1.20. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 50.7% / 49.3%, dominance ratio 0.54, key duel: Johan Manzambi vs Mamadou Sangare

Johan Manzambi xG 0.27Nicolas Jackson xG 0.27Emiliano Buendía xG 0.12Yehor Yarmoliuk xG 0.05Igor Thiago xG 0.49Kevin Schade xG 0.34

Summary

Antagonist matchup analysis for Aston Villa vs Brentford. Most likely scoreline: 1-2. Lambdas derived from 6 home and 6 away individual player duels.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Johan Manzambi vs Mamadou Sangare will be the pivotal duel. Total antagonist xG — Home: 0.87, Away: 1.20. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Ipswich vs Fulham

Premier League · 20261010 · 4-2-3-1 vs 4-2-3-1

Predicted 1-0Winner: IpswichConfidence 0.68λ home/away 1.41 / 1.30Most-likely P 9.2%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Ipswich vs Fulham. 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 1.410, Away 1.302). Final calibrated Poisson lambdas: Home 1.410, Away 1.302 (most likely score 1-0).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.41 / 1.30 Final λ (H/A) 1.41 / 1.30

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

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Ipswich	Fulham
League position	11.00	19.00
Points per game	1.28	0.91
Attack index	1.06	0.86
Defense (concede) index	0.98	1.24
Form multiplier	1.02	0.98
Standing λ multiplier	1.02	1.02

Lambda decomposition (how the goal rates were built)

Stage	Ipswich λ	Fulham λ
FBref Squad Prior E[λ] (weight 0.192)	1.379	1.379
Pre-competitive-floor	1.410	1.302
Pre-calibration (Micro-duels)	1.410	1.302
Final λ	1.410	1.302

Scoreline distribution & markets

Top 5 scorelines	P
1-0	9.2%
1-1	12.3%
2-1	8.6%
0-1	8.5%
1-2	7.9%

Home win	39.5%
Draw	25.9%
Away win	34.5%
Over 2.5	50.9%
BTTS yes	55.1%

Pregame fair line — favorite Ipswich (39.5%), fair total 2.71, fair spread 0.11

Projected players vs season baseline

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

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Emersonn	F	70	0	0.29	0.16	80%	2	0.9	6.8	34.6	10	FBref Prior F_service
Jaden Philogene-Bidace	F	80	0	0.13	0.01	2183%	2	0.2	6.7	10.7	12	XGBoost F_service
Jack Clarke	F	72	0	0.17	0.03	538%	2	0.3	6.9	23.9	17	FBref Prior F_service
Exequiel Palacios	M	84	0	0.02	-	n/a	0	0.0	7.0	31.0	9	FBref Prior M_service
Saša Lukić	M	82	0	0.04	0.03	34%	0	0.4	6.9	46.2	23	FBref Prior M_service
Leif Davis	D	90	1	0.34	0.16	114%	1	0.6	6.7	33.2	10	FBref Prior D_service
Dara O'Shea	D	90	0	0.01	0.01	64%	0	0.1	6.8	31.9	10	FBref Prior D_service
Issa Diop	D	90	0	0.07	0.03	114%	0	0.1	6.8	32.4	27	FBref Prior D_service
Julio Enciso	M	84	0	0.22	0.13	70%	3	1.7	6.9	34.4	10	FBref Prior M_service
Abdoul Ouattara	M	87	0	0.03	0.00	1137%	0	0.1	6.8	44.4	15	FBref Prior M_service
Christian Walton	G	90	0	0.00	-	n/a		0.0	6.9	7.0	10	FBref Prior G_service
Team totals			1	1.41			11			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Kjell Scherpen	G	4.6m	13.6%	Market-value substitute prior
Jacob Greaves	D	14.1m	22.7%	Market-value substitute prior
Darnell Furlong	D	16.0m	60.2%	Market-value substitute prior
Florentino Luís	M	22.6m	52.5%	Market-value substitute prior
Marcelino Núñez	M	22.5m	31.8%	Market-value substitute prior
Abdul Fatawu Issahaku	F	26.1m	35.0%	Market-value substitute prior

Fulham — 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
Ryan Sessegnon	D	86	0.11	0.04	192%	1	0.5	6.8	44.7	28	FBref Prior D_service
Calvin Bassey	D	90	0.04	0.04	ok	1	0.4	6.8	50.9	26	FBref Prior D_service
David Affengruber	D	88	0.04	0.03	65%	1	0.5	6.9	55.3	31	FBref Prior D_service
Timothy Castagne	D	85	0.09	0.06	57%	1	0.5	6.7	49.8	30	FBref Prior D_service
Bernd Leno	G	90	0.00	-	n/a		0.0	7.0	57.2	30	FBref Prior G_service
Sander Berge	M	82	0.06	0.03	76%	1	0.4	6.9	52.3	29	FBref Prior M_service
Shea Charles	M	87	0.03	0.01	273%	1	0.2	6.9	34.6	10	FBref Prior M_service
Josh King	M	77	0.18	0.11	69%	2	0.9	6.9	48.1	27	XGBoost M_service
Oscar Bobb	F	70	0.09	0.06	49%	1	0.5	6.8	47.8	34	FBref Prior F_service
Gonzalo García	F	81	0.38	0.21	75%	2	1.1	6.8	49.1	30	FBref Prior F_service
Alex Iwobi	F	81	0.12	0.06	103%	2	1.0	7.1	49.6	33	FBref Prior F_service
Team totals			1.30			17			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Benjamin Lecomte	G	4.4m	10.9%	Market-value substitute prior
Antonee Robinson	D	14.5m	23.6%	Market-value substitute prior
Joachim Andersen	D	14.4m	23.3%	Market-value substitute prior
Hugo Larsson	M	23.1m	54.9%	Market-value substitute prior
Emile Smith Rowe	M	18.4m	70.6%	Market-value substitute prior
Kevin	F	19.0m	73.9%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Exequiel Palacios vs Sander Berge will be the pivotal duel. Total antagonist xG — Home: 0.92, Away: 0.89. 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 49.7% / 50.3%, dominance ratio 0.49, key duel: Exequiel Palacios vs Sander Berge

Julio Enciso xG 0.22Abdoul Ouattara xG 0.03Jack Clarke xG 0.17Josh King xG 0.18Gonzalo García xG 0.39Oscar Bobb xG 0.10

Summary

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

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Exequiel Palacios vs Sander Berge will be the pivotal duel. Total antagonist xG — Home: 0.92, Away: 0.89. 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 · 20261010 · 4-3-3 vs 3-5-2

Predicted 3-0Winner: BarcelonaConfidence 0.85λ home/away 3.74 / 0.88Most-likely P 8.7%

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 4-3-3 vs 3-5-2 (duel lambdas: Home 3.492, Away 0.878). Final calibrated Poisson lambdas: Home 3.739, Away 0.877 (most likely score 3-0).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 3.49 / 0.88 Final λ (H/A) 3.74 / 0.88

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	2.25	1.25
Attack index	1.80	0.73
Defense (concede) index	0.83	0.92
Form multiplier	1.05	0.95
Standing λ multiplier	1.19	0.85

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	3.562	1.054
Pre-calibration (Micro-duels)	3.492	0.878
Final λ	3.739	0.877

Scoreline distribution & markets

Top 5 scorelines	P
3-0	8.7%
4-0	8.1%
3-1	7.6%
4-1	7.1%
2-0	7.0%

Home win	87.2%
Draw	8.2%
Away win	4.6%
Over 2.5	83.8%
BTTS yes	57.0%

Pregame fair line — favorite Barcelona (87.2%), fair total 4.62, fair spread 2.86

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 (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
Karim Adeyemi	F	79	1	0.70	0.48	47%	3	1.7	7.2	57.9	10	FBref Prior F_service
Gabriel Jesus	F	71	0	0.45	0.11	300%	2	0.7	6.8	35.8	24	XGBoost F_service
Lamine Yamal	F	83	2	1.41	0.52	173%	7	3.6	8.4	67.3	28	FBref Prior F_service
Rodri	M	82	0	0.16	0.08	102%	1	0.7	7.5	68.9	23	FBref Prior M_service
Pedri	M	80	0	0.17	0.05	264%	1	0.6	7.2	64.6	25	FBref Prior M_service
Xavi Espart	D	88	0	0.05	0.01	483%	1	0.2	6.9	26.0	21	FBref Prior D_service
Gerard Martín	D	82	0	0.02	0.01	161%	0	0.2	7.1	56.0	28	FBref Prior D_service
Pau Cubarsí	D	85	0	0.07	0.02	191%	0	0.2	7.2	55.6	29	FBref Prior D_service
Eric García	D	80	0	0.05	0.05	ok	1	0.5	7.0	57.1	28	FBref Prior D_service
Joan García	G	84	0	0.00	-	n/a		0.0	7.1	62.2	28	FBref Prior G_service
Fermín López	M	80	0	0.48	0.28	75%	3	1.9	7.1	63.5	27	FBref Prior M_service
Team totals			3	3.74			21			7.2

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
Jules Koundé	D	12.9m	50.8%	Market-value substitute prior
Alejandro Balde	D	15.2m	37.1%	Market-value substitute prior
Ferran Torres	M	23.6m	57.3%	Market-value substitute prior
Dani Olmo	M	25.5m	59.7%	Market-value substitute prior
Anthony Gordon	F	26.5m	49.8%	Market-value substitute prior

Getafe — 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
Nemanja Gudelj	M	86	0.06	0.03	69%	1	0.9	6.7	61.3	29	FBref Prior M_service
Djené	D	81	0.00	-	n/a	0	0.0	6.7	60.7	26	FBref Prior D_service
David Soria	G	90	0.00	-	n/a		0.0	7.1	68.6	30	FBref Prior G_service
Zaid Romero	D	88	0.03	0.04	33%	1	0.5	6.9	63.7	23	FBref Prior D_service
Andrés García	D	78	0.04	0.02	166%	1	0.5	6.6	44.0	20	FBref Prior D_service
Mario Martín	M	80	0.10	0.09	ok	1	0.8	6.7	59.6	25	FBref Prior M_service
Orel Mangala	M	87	0.03	0.02	55%	1	0.3	6.8	51.1	9	FBref Prior M_service
Enes Ünal	F	87	0.17	0.09	79%	1	0.8	6.6	48.0	27	FBref Prior F_service
Ivan Azón	F	83	0.17	0.13	ok	2	1.9	6.9	50.0	7	XGBoost F_service
Johan Mojica	D	88	0.03	0.02	80%	1	0.4	6.8	59.5	28	FBref Prior D_service
Ramón Terrats	M	81	0.13	0.08	69%	1	1.1	6.9	60.6	28	FBref Prior M_service
Team totals			0.88			13			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
Abdel Abqar	D	6.7m	41.0%	Market-value substitute prior
Yvan Neyou	D	13.6m	29.9%	Market-value substitute prior
Mauro Arambarri	M	22.2m	51.0%	Market-value substitute prior
Veljko Birmančević	M	22.0m	50.0%	Market-value substitute prior
Christantus Uche	F	25.8m	58.1%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~54% possession expected (Pedri vs Mario Martín). Total antagonist xG — Home: 1.94, Away: 0.66. Home danger zone: Right Wing vs Left Wingback — Compact Flank. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 53.8% / 46.2%, dominance ratio 0.64, key duel: Pedri vs Mario Martín

Karim Adeyemi xG 0.42Lamine Yamal xG 0.85Gabriel Jesus xG 0.27Enes Ünal xG 0.17Ivan Azón xG 0.17Ramón Terrats xG 0.13

Summary

Antagonist matchup analysis for Barcelona vs Getafe. Most likely scoreline: 3-0. Lambdas derived from 5 home and 6 away individual player duels.

4-3-3 creates structural superiority against 3-5-2. Home team should exploit wider spaces and numerical advantages in transition. Home midfield dominates with ~54% possession expected (Pedri vs Mario Martín). Total antagonist xG — Home: 1.94, Away: 0.66. Home danger zone: Right Wing vs Left Wingback — Compact Flank. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Arsenal vs Leeds

Premier League · 20261010 · 4-2-3-1 vs 3-4-2-1

Predicted 2-1Winner: ArsenalConfidence 0.76λ home/away 2.11 / 1.17Most-likely P 9.8%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Arsenal vs Leeds. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 3-4-2-1 (duel lambdas: Home 1.891, Away 0.990). Final calibrated Poisson lambdas: Home 2.106, Away 1.167 (most likely score 2-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.89 / 0.99 Final λ (H/A) 2.11 / 1.17

FBref Team Priors: Arsenal (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 1.379) vs Leeds United (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 1.379) | Blend Weight: 0.192

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Arsenal	Leeds
League position	2.00	5.00
Points per game	1.82	1.55
Attack index	1.10	0.94
Defense (concede) index	0.79	0.93
Form multiplier	1.02	0.98
Standing λ multiplier	0.95	0.94

Lambda decomposition (how the goal rates were built)

Stage	Arsenal λ	Leeds λ
FBref Squad Prior E[λ] (weight 0.192)	1.379	1.379
Pre-mismatch	1.986	1.287
Pre-competitive-floor	2.233	1.238
Pre-calibration (Micro-duels)	1.891	0.990
Final λ	2.106	1.167

Scoreline distribution & markets

Top 5 scorelines	P
2-1	9.8%
1-1	9.4%
2-0	8.4%
1-0	7.9%
3-1	6.9%

Home win	58.8%
Draw	20.8%
Away win	20.4%
Over 2.5	63.5%
BTTS yes	60.5%

Pregame fair line — favorite Arsenal (58.8%), fair total 3.27, fair spread 0.94

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.

Arsenal — 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
Jurriën Timber	D	77	0	0.10	0.03	185%	0	0.2	6.7	49.4	19	XGBoost D_service
David Raya	G	90	0	0.00	-	n/a		0.0	6.9	56.7	28	FBref Prior G_service
Cristhian Mosquera	D	81	0	0.01	0.00	182%	0	0.0	6.8	34.5	24	FBref Prior D_service
Gabriel Magalhães	D	90	0	0.14	0.08	84%	1	0.8	6.9	59.5	29	FBref Prior D_service
Riccardo Calafiori	D	79	0	0.14	0.07	105%	1	0.8	6.8	43.7	22	FBref Prior D_service
Bruno Guimarães	M	81	0	0.15	0.14	ok	2	0.8	7.1	52.0	20	FBref Prior M_service
Viktor Gyökeres	F	76	1	0.47	0.21	128%	2	0.9	6.7	48.8	29	FBref Prior F_service
Eberechi Eze	M	74	0	0.17	0.09	88%	2	1.1	6.8	51.6	29	FBref Prior M_service
Martin Ødegaard	M	78	0	0.20	0.07	197%	2	0.5	7.1	51.5	22	FBref Prior M_service
Bukayo Saka	F	83	1	0.52	0.29	80%	3	1.9	7.5	58.5	30	FBref Prior F_service
Declan Rice	M	85	0	0.06	0.04	37%	1	0.7	7.4	59.2	29	FBref Prior M_service
Team totals			2	2.11			16			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Illan Meslier	G	4.6m	11.9%	Market-value substitute prior
William Saliba	D	15.4m	38.0%	Market-value substitute prior
Myles Lewis-Skelly	D	15.1m	24.8%	Market-value substitute prior
Martín Zubimendi	M	18.9m	72.8%	Market-value substitute prior
Gabriel Martinelli	M	23.4m	56.2%	Market-value substitute prior
Noni Madueke	F	24.7m	75.1%	Market-value substitute prior

Leeds — 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
Dominic Calvert-Lewin	F	85	1	0.32	0.42	ok	2	1.8	6.9	55.5	29	FBref Prior F_service
Noah Okafor	F	72	0	0.15	0.12	ok	2	0.9	6.9	55.2	23	FBref Prior F_service
Anton Stach	M	87	0	0.13	0.09	45%	1	1.3	7.0	56.9	24	FBref Prior M_service
Gabriel Gudmundsson	M	83	0	0.03	0.01	284%	1	0.2	6.9	38.5	30	FBref Prior M_service
Ao Tanaka	M	75	0	0.05	0.05	ok	1	0.4	6.9	34.4	30	FBref Prior M_service
Ethan Ampadu	M	90	0	0.03	0.05	34%	1	0.6	7.0	59.6	29	FBref Prior M_service
Jayden Bogle	M	77	0	0.10	0.08	ok	1	0.5	6.8	55.2	26	FBref Prior M_service
James Justin	D	89	0	0.06	0.06	ok	1	0.9	6.9	59.8	32	FBref Prior D_service
Tarik Muharemović	D	90	0	0.11	0.05	131%	1	0.5	7.0	35.8	10	FBref Prior D_service
Nico Elvedi	D	90	0	0.04	0.01	228%	1	0.2	6.8	27.5	10	FBref Prior D_service
James Trafford	G	90	0	0.00	-	n/a		0.0	7.0	14.2	30	FBref Prior G_service
Team totals			1	1.17			14			6.9

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Lucas Perri	G	4.7m	12.2%	Market-value substitute prior
Joe Rodon	D	14.3m	23.2%	Market-value substitute prior
Jaka Bijol	D	14.3m	23.1%	Market-value substitute prior
Sean Longstaff	M	15.1m	70.3%	Market-value substitute prior
Ilia Gruev	M	22.4m	51.6%	Market-value substitute prior
Harry Wilson	F	36.6m	54.7%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~52% possession expected (Declan Rice vs Ethan Ampadu). Total antagonist xG — Home: 1.10, Away: 0.90. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle.

Midfield — possession 51.9% / 48.1%, dominance ratio 0.57, key duel: Declan Rice vs Ethan Ampadu

Martin Ødegaard xG 0.16Eberechi Eze xG 0.14Bukayo Saka xG 0.42Dominic Calvert-Lewin xG 0.35Noah Okafor xG 0.16Gabriel Gudmundsson xG 0.03

Summary

Antagonist matchup analysis for Arsenal vs Leeds. Most likely scoreline: 2-1. Lambdas derived from 4 home and 7 away individual player duels.

Tactical parity between 4-2-3-1 and 3-4-2-1. Match outcome driven primarily by individual player quality. Home midfield dominates with ~52% possession expected (Declan Rice vs Ethan Ampadu). Total antagonist xG — Home: 1.10, Away: 0.90. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle.

Man Utd vs Tottenham

Premier League · 20261010 · 4-2-3-1 vs 4-2-3-1

Predicted 1-0Winner: Man UtdConfidence 0.73λ home/away 1.54 / 1.20Most-likely P 9.8%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Man Utd vs Tottenham. 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 1.542, Away 1.200). Final calibrated Poisson lambdas: Home 1.542, Away 1.200 (most likely score 1-0).

Home Starters 11/11 XGBoost (11 FBref) Away Starters 11/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.54 / 1.20 Final λ (H/A) 1.54 / 1.20

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	Man Utd	Tottenham
League position	12.00	20.00
Points per game	1.19	0.91
Attack index	1.10	0.74
Defense (concede) index	0.98	1.10
Form multiplier	1.02	0.98
Standing λ multiplier	1.04	0.92

Lambda decomposition (how the goal rates were built)

Stage	Man Utd λ	Tottenham λ
Pre-competitive-floor	1.542	1.200
Pre-calibration (Micro-duels)	1.542	1.200
Final λ	1.542	1.200

Scoreline distribution & markets

Top 5 scorelines	P
1-0	9.8%
1-1	12.0%
2-1	9.2%
2-0	7.7%
0-1	7.6%

Home win	45.1%
Draw	25.4%
Away win	29.5%
Over 2.5	51.7%
BTTS yes	55.0%

Pregame fair line — favorite Man Utd (45.1%), fair total 2.74, fair spread 0.34

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.

Man Utd — 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
Matheus Cunha	F	84	0	0.18	0.11	62%	2	1.8	7.0	55.3	28	FBref Prior F_service
Marcus Rashford	F	78	0	0.21	0.15	34%	2	1.5	7.1	50.0	33	FBref Prior F_service
Bruno Fernandes	M	89	1	0.32	0.23	40%	3	2.1	7.4	62.7	28	FBref Prior M_service
Bryan Mbeumo	F	85	0	0.35	0.40	ok	2	2.2	7.0	56.6	32	FBref Prior F_service
Kobbie Mainoo	M	86	0	0.06	0.03	133%	1	0.6	7.2	58.2	27	FBref Prior M_service
Youri Tielemans	M	84	0	0.07	0.05	30%	1	0.8	7.2	56.3	22	FBref Prior M_service
Lisandro Martínez	D	88	0	0.04	0.02	166%	1	0.5	7.1	50.8	21	FBref Prior D_service
Harry Maguire	D	89	0	0.05	0.04	ok	1	0.6	6.9	53.5	26	FBref Prior D_service
Diogo Dalot	D	88	0	0.08	0.04	111%	1	0.8	6.8	53.2	28	FBref Prior D_service
Senne Lammens	G	90	0	0.00	-	n/a		0.0	7.0	59.0	29	FBref Prior G_service
Luke Shaw	D	84	0	0.02	0.02	ok	1	0.4	6.8	55.6	28	FBref Prior D_service
Team totals			1	1.54			17			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
André Onana	G	4.7m	12.3%	Market-value substitute prior
Leny Yoro	D	16.1m	63.2%	Market-value substitute prior
Ayden Heaven	D	14.7m	24.1%	Market-value substitute prior
Carlos Baleba	M	23.5m	57.0%	Market-value substitute prior
Andrey Santos	M	16.5m	52.7%	Market-value substitute prior
Benjamin Šeško	F	22.1m	75.5%	Market-value substitute prior

Tottenham — 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
Antonín Kinský	G	90	0.00	-	n/a		0.0	7.0	27.9	29	FBref Prior G_service
Archie Gray	M	81	0.06	0.04	48%	1	0.4	6.8	45.7	33	FBref Prior M_service
Jan Paul van Hecke	D	90	0.15	0.08	86%	1	0.6	7.2	59.3	28	FBref Prior D_service
Micky van de Ven	D	88	0.07	0.05	35%	1	0.3	6.8	54.8	27	FBref Prior D_service
Destiny Udogie	D	80	0.01	0.00	89%	0	0.1	6.6	42.4	20	FBref Prior D_service
Dominic Solanke	F	75	0.21	0.12	80%	2	1.0	6.6	50.5	24	FBref Prior F_service
Omar Marmoush	F	77	0.19	0.07	175%	2	1.1	6.7	38.5	28	XGBoost F_service
Mohammed Kudus	F	73	0.09	0.02	289%	1	0.5	6.9	34.4	20	FBref Prior F_service
Sávio	F	81	0.16	0.09	74%	2	0.8	6.9	36.9	28	XGBoost F_service
Sandro Tonali	M	84	0.08	0.06	32%	1	1.2	7.2	56.2	26	FBref Prior M_service
Mateus Fernandes	M	80	0.06	0.04	51%	1	0.8	6.9	59.1	29	FBref Prior M_service
Team totals			1.20			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
Xavi Simons	M	23.4m	56.3%	Market-value substitute prior
Djed Spence	M	23.4m	56.1%	Market-value substitute prior
Mykhailo Mudryk	F	26.7m	62.2%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Kobbie Mainoo vs Sandro Tonali will be the pivotal duel. Total antagonist xG — Home: 1.06, Away: 0.92. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.6% / 50.4%, dominance ratio 0.50, key duel: Kobbie Mainoo vs Sandro Tonali

Bruno Fernandes xG 0.29Matheus Cunha xG 0.16Marcus Rashford xG 0.18Sandro Tonali xG 0.08Omar Marmoush xG 0.20Dominic Solanke xG 0.23

Summary

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

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Kobbie Mainoo vs Sandro Tonali will be the pivotal duel. Total antagonist xG — Home: 1.06, Away: 0.92. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Real Madrid vs Villarreal

LaLiga · 20261010 · 4-2-3-1 vs 4-4-2

Predicted 3-1Winner: Real MadridConfidence 0.79λ home/away 3.39 / 1.74Most-likely P 6.7%

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 4-2-3-1 vs 4-4-2 (duel lambdas: Home 3.157, Away 1.598). Final calibrated Poisson lambdas: Home 3.394, Away 1.744 (most likely score 3-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 3.16 / 1.60 Final λ (H/A) 3.39 / 1.74

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	1.79	1.25
Attack index	1.32	1.03
Defense (concede) index	0.99	0.96
Form multiplier	1.03	0.97
Standing λ multiplier	1.12	0.99

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	3.220	1.918
Pre-calibration (Micro-duels)	3.157	1.598
Final λ	3.394	1.744

Scoreline distribution & markets

Top 5 scorelines	P
3-1	6.7%
2-1	5.9%
3-2	5.8%
4-1	5.7%
2-2	5.1%

Home win	69.2%
Draw	14.3%
Away win	16.6%
Over 2.5	88.6%
BTTS yes	79.8%

Pregame fair line — favorite Real Madrid (69.2%), fair total 5.14, fair spread 1.65

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.

Real Madrid — 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
Kylian Mbappé	F	89	2	1.29	0.70	85%	5	4.3	7.9	64.2	23	FBref Prior F_service
Vinícius Júnior	F	80	1	0.55	0.39	40%	3	2.8	7.2	69.8	34	FBref Prior F_service
Jude Bellingham	M	83	0	0.35	0.17	101%	2	1.6	7.1	66.8	23	FBref Prior M_service
Arda Güler	M	69	0	0.37	0.12	198%	2	1.2	7.1	67.3	24	FBref Prior M_service
Aurélien Tchouaméni	M	79	0	0.09	0.07	32%	1	1.3	7.0	62.7	23	XGBoost M_service
Bernardo Silva	M	78	0	0.11	0.09	ok	1	0.9	7.0	62.0	29	FBref Prior M_service
Álvaro Carreras	D	82	0	0.08	0.02	357%	0	0.2	6.9	43.1	26	FBref Prior D_service
Ibrahima Konaté	D	89	0	0.08	0.03	218%	1	0.3	6.8	60.9	28	FBref Prior D_service
Antonio Rüdiger	D	88	0	0.09	0.04	115%	1	0.5	6.9	41.8	25	FBref Prior D_service
Denzel Dumfries	M	84	0	0.14	0.04	220%	1	0.8	6.7	40.5	16	FBref Prior M_service
Thibaut Courtois	G	90	0	0.00	-	n/a		0.0	7.0	63.0	23	FBref Prior G_service
Team totals			3	3.39			20			7.1

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
Dean Huijsen	D	15.3m	25.2%	Market-value substitute prior
Marc Cucurella	D	26.6m	50.8%	Market-value substitute prior
Federico Valverde	M	23.8m	34.3%	Market-value substitute prior
Eduardo Camavinga	M	17.2m	59.4%	Market-value substitute prior
Yan Diomande	F	23.2m	75.6%	Market-value substitute prior

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Péter Gulácsi	G	90	0	0.00	-	n/a		0.0	6.9	25.1	9	FBref Prior G_service
Santiago Mouriño	D	83	0	0.05	0.03	40%	1	0.4	6.8	56.7	29	FBref Prior D_service
Pau Navarro	D	85	0	0.01	0.00	247%	0	0.0	6.8	43.5	31	FBref Prior D_service
Renato Veiga	D	90	0	0.02	0.01	147%	0	0.2	7.2	59.1	29	FBref Prior D_service
Gerard Moreno	F	77	0	0.31	0.24	ok	2	1.3	7.1	56.6	26	FBref Prior F_service
Ayoze Pérez	F	68	0	0.41	0.27	52%	2	1.2	6.8	57.1	27	FBref Prior F_service
Pape Gueye	M	78	0	0.14	0.15	ok	1	1.2	7.1	61.7	28	FBref Prior M_service
Santi Comesaña	M	73	0	0.06	0.08	ok	1	0.4	6.9	62.4	27	FBref Prior M_service
Ilias Akhomach	F	73	0	0.13	0.06	110%	1	0.9	6.9	52.0	25	FBref Prior F_service
Sergi Cardona	D	88	0	0.05	0.01	269%	1	0.4	6.8	45.5	31	FBref Prior D_service
Alberto Moleiro	F	77	1	0.42	0.13	212%	2	1.0	7.4	60.8	39	FBref Prior F_service
Team totals			1	1.74			13			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Luiz Júnior	G	4.8m	12.9%	Market-value substitute prior
Carlos Romero	D	14.5m	23.6%	Market-value substitute prior
Logan Costa	D	14.1m	32.3%	Market-value substitute prior
Tajon Buchanan	M	28.2m	57.3%	Market-value substitute prior
Nathan-Dylan Saliba	M	22.3m	51.2%	Market-value substitute prior
Georges Mikautadze	F	26.5m	35.8%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~52% possession expected (Jude Bellingham vs Pape Gueye). Total antagonist xG — Home: 1.72, Away: 1.04. 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 51.8% / 48.2%, dominance ratio 0.58, key duel: Jude Bellingham vs Pape Gueye

Arda Güler xG 0.22Bernardo Silva xG 0.06Jude Bellingham xG 0.21Ayoze Pérez xG 0.30Alberto Moleiro xG 0.30Gerard Moreno xG 0.22

Summary

Antagonist matchup analysis for Real Madrid vs Villarreal. Most likely scoreline: 3-1. Lambdas derived from 7 home and 6 away individual player duels.

4-2-3-1 creates structural superiority against 4-4-2. Home team should exploit wider spaces and numerical advantages in transition. Home midfield dominates with ~52% possession expected (Jude Bellingham vs Pape Gueye). Total antagonist xG — Home: 1.72, Away: 1.04. 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 2026-10-10 13:38:17 UTC · Soccer prediction reporting