Soccer predictions: actual data vs predicted data

Slate 20260912 · 11 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
R. Racing Club vs Alavés LaLiga	0-1	Alavés	32.7% / 29.9% / 37.4%	35.9%	43.0%	0.62	1.02 / 1.11	-	pending
Sunderland vs Arsenal Premier League	0-1	Arsenal	21.3% / 22.9% / 55.8%	55.1%	54.7%	0.67	1.05 / 1.84	-	pending
Bournemouth vs Brentford Premier League	0-1	Brentford	29.9% / 27.7% / 42.3%	42.5%	48.0%	0.64	1.06 / 1.32	-	pending
Athletic Club vs Elche LaLiga	1-0	Athletic Club	51.3% / 24.7% / 24.1%	50.6%	52.6%	0.67	1.65 / 1.05	-	pending
Osasuna vs Espanyol LaLiga	1-0	Osasuna	36.4% / 28.7% / 34.8%	39.9%	46.5%	0.63	1.16 / 1.12	-	pending
Tottenham vs Everton Premier League	0-1	Everton	32.7% / 29.9% / 37.4%	35.9%	43.0%	0.61	1.02 / 1.11	-	pending
Liverpool vs Fulham Premier League	2-0	Liverpool	73.6% / 15.3% / 11.0%	70.0%	57.2%	0.73	2.67 / 0.95	-	pending
Chelsea vs Hull Premier League	3-1	Chelsea	83.0% / 9.7% / 7.3%	87.8%	68.8%	0.75	3.82 / 1.22	-	pending
Crystal Palace vs Ipswich Premier League	2-1	Crystal Palace	45.1% / 23.8% / 31.1%	59.3%	61.1%	0.64	1.70 / 1.37	-	pending
Aston Villa vs Forest Premier League	1-1	Draw	35.4% / 31.1% / 33.5%	32.4%	40.2%	0.61	1.02 / 0.98	-	pending
Real Madrid vs Rayo Vallecano LaLiga	4-1	Real Madrid	87.1% / 7.6% / 5.3%	91.0%	69.1%	0.77	4.29 / 1.21	-	pending

Match detail

R. Racing Club vs Alavés

LaLiga · 20260912 · 4-2-3-1 vs 5-3-2

Predicted 0-1Winner: AlavésConfidence 0.62λ home/away 1.02 / 1.11Most-likely P 13.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for R. Racing Club vs Alavés. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 5-3-2 (duel lambdas: Home 0.898, Away 1.111). Final calibrated Poisson lambdas: Home 1.020, Away 1.111 (most likely score 0-1).

Home Starters 11/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.90 / 1.11 Final λ (H/A) 1.02 / 1.11

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	R. Racing Club	Alavés
League position	13.00	2.00
Points per game	1.00	2.50
Attack index	1.46	2.08
Defense (concede) index	0.62	1.67
Form multiplier	0.95	1.05
Standing λ multiplier	0.95	1.65

Lambda decomposition (how the goal rates were built)

Stage	R. Racing Club λ	Alavés λ
Pre-competitive-floor	0.898	1.111
Pre-calibration (Micro-duels)	0.898	1.111
Final λ	1.020	1.111

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

Scoreline distribution & markets

Top 5 scorelines	P
0-1	13.1%
1-1	13.6%
0-0	12.0%
1-0	12.0%
1-2	7.5%

Home win	32.7%
Draw	29.9%
Away win	37.4%
Over 2.5	35.9%
BTTS yes	43.0%

Pregame fair line — favorite Alavés (37.4%), fair total 2.13, fair spread -0.09

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.

R. Racing 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
Yassir Zabiri	F	52	0.19	0.15	ok	2	1.2	7.0	56.0	5	FBref Prior F_service
Iñigo Vicente	M	84	0.05	0.01	463%	1	0.2	6.8	58.0	5	FBref Prior M_service
Sergio Canales	M	78	0.11	0.17	36%	4	2.4	6.8	54.2	5	FBref Prior M_service
Pablo García	M	89	0.06	0.11	47%	3	1.2	6.4	56.2	5	FBref Prior M_service
Matteo Prati	M	43	0.03	-	n/a	2	0.0	6.8	44.0	3	FBref Prior M_service
Iván Martín	M	74	0.05	0.01	255%	1	0.2	6.8	53.0	4	FBref Prior M_service
Jorge Salinas	D	90	0.20	0.04	357%	1	0.2	6.6	53.2	5	FBref Prior D_service
Jeanuël Belocian	D	36	0.09	0.04	94%	1	0.5	6.8	36.0	2	XGBoost D_service
Pablo Ramón	D	66	0.00	-	n/a	0	0.0	6.6	42.4	5	FBref Prior D_service
Alvaro Mantilla	D	88	0.16	0.03	345%	1	0.4	6.5	50.4	5	XGBoost D_service
Julen Agirrezabala	G	91	0.00	-	n/a	0	0.0	7.1	54.2	5	FBref Prior G_service
Team totals			1.02			17			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
Andrés Martín	M	22.2m	51.0%	Market-value substitute prior
Giorgi Guliashvili	F	25.3m	56.0%	Market-value substitute prior

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	89	0	0.00	-	n/a	0	0.0	7.1	56.5	4	FBref Prior G_service
Ángel Pérez	M	88	0	0.19	0.09	120%	1	1.0	6.8	57.2	4	FBref Prior M_service
Ville Koski	D	85	0	0.00	-	n/a	0	0.0	6.7	48.8	4	FBref Prior D_service
Nahuel Tenaglia	D	88	0	0.04	0.02	106%	2	0.8	6.7	49.8	4	FBref Prior D_service
Lucas Boyé	F	76	1	0.26	0.22	ok	2	2.0	7.6	60.2	4	FBref Prior F_service
Mariano Díaz	F	44	0	0.23	0.12	97%	1	0.8	6.7	55.8	4	XGBoost F_service
Carles Aleñá	M	40	0	0.05	0.02	116%	1	0.2	6.7	33.0	4	FBref Prior M_service
Antonio Blanco	M	91	0	0.07	0.03	148%	2	0.8	6.9	53.0	4	FBref Prior M_service
Pablo Ibáñez	M	89	0	0.13	0.09	42%	2	1.5	6.8	54.5	4	FBref Prior M_service
Abderrahman Rebbach	M	70	0	0.05	0.00	965%	1	0.2	6.6	47.8	4	XGBoost M_service
Jonny Otto	D	78	0	0.01	0.00	232%	1	0.2	6.4	52.0	4	XGBoost D_service
Team totals			1	1.11			14			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Adrián Rodríguez	G	4.4m	10.9%	Market-value substitute prior
Youssef Enriquez	D	13.6m	30.2%	Market-value substitute prior
Nicolás Valentini	D	13.6m	29.9%	Market-value substitute prior
Miguel Rodríguez	M	22.0m	50.1%	Market-value substitute prior
Ander Guevara	M	22.0m	49.9%	Market-value substitute prior
Toni Martínez	F	25.5m	56.8%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Pablo García vs Antonio Blanco will be the pivotal duel. Total antagonist xG — Home: 0.43, Away: 0.33. 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 49.9% / 50.1%, dominance ratio 0.51, key duel: Pablo García vs Antonio Blanco

Sergio Canales xG 0.09Pablo García xG 0.05Matteo Prati xG 0.04Lucas Boyé xG 0.22Jonny Otto xG 0.01Abderrahman Rebbach xG 0.04

Summary

Antagonist matchup analysis for R. Racing Club vs Alavés. Most likely scoreline: 0-1. Lambdas derived from 5 home and 4 away individual player duels.

Tactical parity between 4-2-3-1 and 5-3-2. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Pablo García vs Antonio Blanco will be the pivotal duel. Total antagonist xG — Home: 0.43, Away: 0.33. 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 Arsenal

Premier League · 20260912 · 4-2-3-1 vs 4-2-3-1

Predicted 0-1Winner: ArsenalConfidence 0.67λ home/away 1.05 / 1.84Most-likely P 10.2%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Sunderland vs Arsenal. 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 0.866, Away 1.642). Final calibrated Poisson lambdas: Home 1.050, Away 1.839 (most likely score 0-1).

Home Starters 11/11 XGBoost (11 FBref) Away Starters 9/11 XGBoost (11 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.87 / 1.64 Final λ (H/A) 1.05 / 1.84

FBref Team Priors: Sunderland (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 1.481) vs Arsenal (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 1.481) | 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	Arsenal
League position	12.00	2.00
Points per game	1.33	3.00
Attack index	1.25	1.25
Defense (concede) index	0.21	1.25
Form multiplier	0.94	1.06
Standing λ multiplier	0.63	1.21

Lambda decomposition (how the goal rates were built)

Stage	Sunderland λ	Arsenal λ
FBref Squad Prior E[λ] (weight 0.192)	1.481	1.481
Pre-mismatch	0.866	1.642
Pre-competitive-floor	0.835	1.839
Pre-calibration (Micro-duels)	0.866	1.642
Final λ	1.050	1.839

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

Scoreline distribution & markets

Top 5 scorelines	P
0-1	10.2%
1-1	10.8%
1-2	9.9%
0-2	9.4%
1-3	6.1%

Home win	21.3%
Draw	22.9%
Away win	55.8%
Over 2.5	55.1%
BTTS yes	54.7%

Pregame fair line — favorite Arsenal (55.8%), fair total 2.89, fair spread -0.79

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 xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Brian Brobbey	F	80	0.25	0.15	68%	2	1.5	7.4	48.0	4	FBref Prior F_service
Nilson Angulo	M	64	0.13	0.04	246%	2	0.5	7.1	52.2	4	FBref Prior M_service
Enzo Le Fée	M	91	0.18	0.30	40%	4	1.8	7.3	51.8	4	FBref Prior M_service
Thomas Meunier	D	88	0.07	0.05	43%	1	1.0	6.6	48.5	4	FBref Prior D_service
Noah Sadiki	M	91	0.18	0.09	104%	2	1.2	7.5	51.8	4	FBref Prior M_service
Granit Xhaka	M	90	0.08	0.01	435%	1	0.2	7.0	57.8	4	FBref Prior M_service
Reinildo Mandava	D	89	0.00	-	n/a	0	0.0	6.5	51.5	4	FBref Prior D_service
Daniel Ballard	D	94	0.06	0.02	192%	1	0.5	7.1	51.8	4	FBref Prior D_service
Kevin Danso	D	93	0.00	-	n/a	0	0.0	7.0	24.3	3	FBref Prior D_service
Nordi Mukiele	D	92	0.00	-	n/a	0	0.0	6.8	37.5	4	FBref Prior D_service
Robin Roefs	G	95	0.00	-	n/a	0	0.0	7.7	51.2	4	FBref Prior G_service
Team totals			1.05			14			7.1

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Melker Ellborg	G	4.4m	10.9%	Market-value substitute prior
Trai Hume	D	14.3m	23.3%	Market-value substitute prior
Omar Alderete	D	19.5m	61.2%	Market-value substitute prior
Habib Diarra	M	18.7m	71.8%	Market-value substitute prior
Malick Fofana	M	23.1m	54.8%	Market-value substitute prior
Wilson Isidor	F	25.4m	73.3%	Market-value substitute prior

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
Kai Havertz	F	95	1	0.35	0.11	219%	2	1.0	7.6	43.2	5	FBref Prior F_service
Christos Tzolis	M	76	0	0.19	0.04	401%	3	0.8	7.6	42.6	5	FBref Prior M_service
Martin Ødegaard	M	83	0	0.21	0.20	ok	2	1.2	7.8	49.0	5	FBref Prior M_service
Bukayo Saka	F	90	0	0.34	0.25	35%	3	1.5	7.5	37.3	6	FBref Prior F_service
Declan Rice	M	91	0	0.09	0.02	338%	2	0.6	7.9	44.8	5	FBref Prior M_service
Myles Lewis-Skelly	D	90	0	0.03	0.03	ok	1	0.5	7.3	35.3	6	FBref Prior D_service
Riccardo Calafiori	D	87	0	0.20	0.11	91%	2	0.8	7.3	42.8	5	FBref Prior D_service
Gabriel Magalhães	D	95	0	0.18	0.10	89%	3	0.8	7.4	41.0	5	FBref Prior D_service
Ezri Konsa	D	55	0	0.00	-	n/a	0	0.0	7.3	33.8	4	FBref Prior D_service
Ben White	D	95	0	0.20	0.04	456%	0	0.2	7.1	43.4	5	FBref Prior D_service
David Raya	G	95	0	0.00	-	n/a	0	0.0	7.8	40.8	5	FBref Prior G_service
Team totals			1	1.84			18			7.5

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
Jurriën Timber	D	15.3m	37.7%	Market-value substitute prior
Martín Zubimendi	M	18.9m	72.8%	Market-value substitute prior
Bruno Guimarães	M	21.7m	72.7%	Market-value substitute prior
Viktor Gyökeres	F	26.9m	63.4%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~53% possession expected (Noah Sadiki vs Declan Rice). Total antagonist xG — Home: 0.44, Away: 0.77. 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 0.44, key duel: Noah Sadiki vs Declan Rice

Nilson Angulo xG 0.09Enzo Le Fée xG 0.08Brian Brobbey xG 0.17Christos Tzolis xG 0.21Bukayo Saka xG 0.33Martin Ødegaard xG 0.23

Summary

Antagonist matchup analysis for Sunderland vs Arsenal. Most likely scoreline: 0-1. Lambdas derived from 4 home and 3 away individual player duels.

Tactical parity between 4-2-3-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~53% possession expected (Noah Sadiki vs Declan Rice). Total antagonist xG — Home: 0.44, Away: 0.77. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Bournemouth vs Brentford

Premier League · 20260912 · 4-2-3-1 vs 4-2-3-1

Predicted 0-1Winner: BrentfordConfidence 0.64λ home/away 1.06 / 1.32Most-likely P 12.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Bournemouth 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 1.063, Away 1.318). Final calibrated Poisson lambdas: Home 1.063, Away 1.318 (most likely score 0-1).

Home Starters 11/11 XGBoost (11 FBref) Away Starters 11/11 XGBoost (11 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.06 / 1.32 Final λ (H/A) 1.06 / 1.32

FBref Team Priors: Bournemouth (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 1.481) vs Brentford (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 1.481) | 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	Bournemouth	Brentford
League position	15.00	5.00
Points per game	0.67	1.67
Attack index	1.67	1.04
Defense (concede) index	0.42	2.08
Form multiplier	0.95	1.05
Standing λ multiplier	0.86	1.39

Lambda decomposition (how the goal rates were built)

Stage	Bournemouth λ	Brentford λ
FBref Squad Prior E[λ] (weight 0.192)	1.481	1.481
Pre-competitive-floor	1.063	1.318
Pre-calibration (Micro-duels)	1.063	1.318
Final λ	1.063	1.318

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

Scoreline distribution & markets

Top 5 scorelines	P
0-1	12.1%
1-1	13.1%
1-0	9.7%
0-0	9.4%
1-2	8.5%

Home win	29.9%
Draw	27.7%
Away win	42.3%
Over 2.5	42.5%
BTTS yes	48.0%

Pregame fair line — favorite Brentford (42.3%), fair total 2.38, fair spread -0.26

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.

Bournemouth — 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
James Hill	D	95	0.00	-	n/a	0	0.0	7.1	51.8	4	FBref Prior D_service
Adam Smith	D	88	0.01	0.00	155%	0	0.2	6.6	47.0	4	FBref Prior D_service
Đorđe Petrović	G	95	0.00	-	n/a	0	0.0	7.5	53.0	4	FBref Prior G_service
António Silva	D	95	0.13	0.07	99%	2	0.5	7.2	52.5	4	FBref Prior D_service
Adrien Truffert	D	95	0.01	0.00	334%	0	0.2	7.1	51.2	4	FBref Prior D_service
Alex Scott	M	95	0.11	0.08	35%	1	1.0	7.7	55.2	4	FBref Prior M_service
Evanilson	F	88	0.16	0.18	ok	3	1.5	7.2	50.5	4	FBref Prior F_service
Marcus Tavernier	M	94	0.19	0.38	48%	4	2.2	7.3	58.5	4	FBref Prior M_service
Justin Kluivert	M	81	0.09	0.19	52%	3	1.8	7.1	49.2	4	FBref Prior M_service
Rayan	M	95	0.13	0.12	ok	3	1.8	7.5	46.8	4	FBref Prior M_service
Tyler Adams	M	39	0.05	-	n/a	0	0.0	7.2	49.8	4	FBref Prior M_service
Team totals			1.06			17			7.2

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
Veljko Milosavljević	D	14.3m	33.1%	Market-value substitute prior
Amine Adli	M	22.7m	53.0%	Market-value substitute prior
Ben Gannon-Doak	M	11.2m	70.3%	Market-value substitute prior
Eli Junior Kroupi	F	27.0m	63.7%	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	95	1	0.22	0.58	61%	4	2.2	7.4	49.0	4	FBref Prior F_service
Kevin Schade	M	95	0	0.12	0.19	40%	4	2.0	7.5	54.5	4	FBref Prior M_service
Mikkel Damsgaard	M	60	0	0.05	0.01	560%	2	0.5	7.4	55.2	4	FBref Prior M_service
Jaidon Anthony	M	63	0	0.07	0.06	ok	2	1.3	7.1	67.7	3	FBref Prior M_service
Vitaly Janelt	M	93	0	0.05	0.13	63%	1	0.8	7.1	57.0	4	FBref Prior M_service
Mamadou Sangare	M	76	0	0.09	0.10	ok	3	1.5	7.6	51.2	4	FBref Prior M_service
Keane Lewis-Potter	D	94	0	0.28	0.26	ok	3	1.5	7.1	51.0	4	FBref Prior D_service
Jannik Schuster	D	75	0	0.08	0.03	218%	1	0.2	7.1	18.2	4	FBref Prior D_service
Kristoffer Ajer	D	95	0	0.09	0.03	237%	1	0.2	7.1	52.2	4	FBref Prior D_service
Michael Kayode	D	75	0	0.16	0.14	ok	3	1.5	7.3	53.8	4	FBref Prior D_service
Caoimhin Kelleher	G	95	0	0.00	-	n/a	0	0.0	7.5	54.2	4	FBref Prior G_service
Team totals			1	1.32			26			7.3

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
Dango Ouattara	M	27.0m	52.5%	Market-value substitute prior
Yehor Yarmoliuk	M	23.0m	71.5%	Market-value substitute prior
Gustavo Nunes	F	25.5m	57.0%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Rayan vs Mamadou Sangare will be the pivotal duel. Total antagonist xG — Home: 0.71, Away: 0.65. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 49.9% / 50.1%, dominance ratio 0.52, key duel: Rayan vs Mamadou Sangare

Marcus Tavernier xG 0.20Justin Kluivert xG 0.11Rayan xG 0.11Kevin Schade xG 0.17Mikkel Damsgaard xG 0.08Jaidon Anthony xG 0.06

Summary

Antagonist matchup analysis for Bournemouth vs Brentford. Most likely scoreline: 0-1. 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 — Rayan vs Mamadou Sangare will be the pivotal duel. Total antagonist xG — Home: 0.71, Away: 0.65. Home danger zone: Left Wing vs Right Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Athletic Club vs Elche

LaLiga · 20260912 · 4-2-3-1 vs 5-3-2

Predicted 1-0Winner: Athletic ClubConfidence 0.67λ home/away 1.65 / 1.05Most-likely P 11.0%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Athletic Club vs Elche. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 5-3-2 (duel lambdas: Home 1.649, Away 0.841). Final calibrated Poisson lambdas: Home 1.649, Away 1.050 (most likely score 1-0).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 10/11 XGBoost (9 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.65 / 0.84 Final λ (H/A) 1.65 / 1.05

FBref Team Priors: Athletic Club (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.741) vs Elche (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 0.741) | 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	Athletic Club	Elche
League position	10.00	19.00
Points per game	1.50	0.25
Attack index	1.25	1.04
Defense (concede) index	2.50	1.04
Form multiplier	1.05	0.95
Standing λ multiplier	1.62	1.02

Lambda decomposition (how the goal rates were built)

Stage	Athletic Club λ	Elche λ
FBref Squad Prior E[λ] (weight 0.228)	0.741	0.741
Pre-competitive-floor	1.649	0.841
Pre-calibration (Micro-duels)	1.649	0.841
Final λ	1.649	1.050

Scoreline distribution & markets

Top 5 scorelines	P
1-0	11.0%
1-1	11.7%
2-1	9.6%
2-0	9.2%
0-1	7.0%

Home win	51.3%
Draw	24.7%
Away win	24.1%
Over 2.5	50.6%
BTTS yes	52.6%

Pregame fair line — favorite Athletic Club (51.3%), fair total 2.70, fair spread 0.60

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.

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
Oihan Sancet	M	88	0	0.32	0.31	ok	3	2.2	7.4	55.0	5	FBref Prior M_service
Robert Navarro	M	56	1	0.16	0.18	ok	2	0.8	6.9	45.0	5	XGBoost M_service
Iñigo Ruiz de Galarreta	M	45	0	0.06	0.01	772%	1	0.2	6.8	40.8	5	FBref Prior M_service
Yuri Berchiche	D	62	0	0.06	0.01	359%	2	0.8	6.6	42.8	4	FBref Prior D_service
Aymeric Laporte	D	76	0	0.54	0.09	524%	2	0.4	6.8	54.6	5	FBref Prior D_service
Yeray Álvarez	D	74	0	0.10	0.03	210%	1	0.6	6.6	40.0	5	FBref Prior D_service
Jesús Areso	D	77	0	0.09	0.01	524%	1	0.2	6.6	39.8	5	FBref Prior D_service
Unai Simón	G	94	0	0.00	-	n/a	0	0.0	8.0	60.2	5	FBref Prior G_service
Nico Williams	M	74	0	0.14	0.18	ok	2	1.2	7.4	54.8	5	FBref Prior M_service
Iñaki Williams	M	59	0	0.08	0.20	60%	2	1.4	6.7	51.8	5	FBref Prior M_service
Beñat Gerenabarrena	M	69	0	0.04	0.01	559%	1	0.2	6.7	53.6	5	FBref Prior M_service
Team totals			1	1.65			17			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
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
Beñat Prados	M	22.6m	52.5%	Market-value substitute prior
Gorka Guruzeta	F	25.7m	46.4%	Market-value substitute prior

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Tete Morente	F	37	0.13	0.01	2046%	2	0.3	6.6	43.5	6	FBref Prior F_service
Fernando Niño	F	78	0.19	0.39	52%	2	1.6	6.9	56.6	5	FBref Prior F_service
Abiel Osorio	F	34	0.16	0.26	37%	3	1.5	6.3	30.5	2	FBref Prior F_service
Gonzalo Villar	M	83	0.06	0.04	46%	1	0.8	6.8	54.4	5	FBref Prior M_service
Thomas Lemar	M	34	0.08	0.06	ok	3	1.5	6.9	40.0	2	XGBoost M_service
Javi Morcillo	M	42	0.03	-	n/a	1	0.0	6.7	39.2	5	FBref Prior M_service
Germán Valera	M	80	0.11	0.00	4420%	1	0.2	6.9	50.8	5	FBref Prior M_service
Víctor Chust	D	89	0.14	0.07	92%	2	0.4	6.9	52.8	5	FBref Prior D_service
Kevin Lomónaco	D	90	0.01	-	n/a	0	-	6.9	-	1	Prior D_service
Buba Sangaré	D	85	0.03	0.01	256%	1	0.2	6.4	48.6	5	FBref Prior D_service
Matías Dituro	G	88	0.00	-	n/a	0	0.0	7.1	48.2	5	FBref Prior G_service
Team totals			1.05			18			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Alejandro Iturbe	G	4.4m	10.9%	Market-value substitute prior
David Affengruber	D	14.3m	23.1%	Market-value substitute prior
Roy Revivo	D	13.7m	30.2%	Market-value substitute prior
Facundo Buonanotte	M	24.9m	50.7%	Market-value substitute prior
Martim Neto	M	24.8m	50.0%	Market-value substitute prior
Ezequiel Ponce	F	30.1m	72.0%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~52% possession expected (Nico Williams vs Germán Valera). Total antagonist xG — Home: 0.54, Away: 0.50. Home danger zone: LW vs RWB + CB. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 52.5% / 47.5%, dominance ratio 0.58, key duel: Nico Williams vs Germán Valera

Oihan Sancet xG 0.24Robert Navarro xG 0.10Iñaki Williams xG 0.07Fernando Niño xG 0.24Víctor Chust xG 0.17Javi Morcillo xG 0.03

Summary

Antagonist matchup analysis for Athletic Club vs Elche. Most likely scoreline: 1-0. Lambdas derived from 4 home and 4 away individual player duels.

Tactical parity between 4-2-3-1 and 5-3-2. Match outcome driven primarily by individual player quality. Home midfield dominates with ~52% possession expected (Nico Williams vs Germán Valera). Total antagonist xG — Home: 0.54, Away: 0.50. Home danger zone: LW vs RWB + CB. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Osasuna vs Espanyol

LaLiga · 20260912 · 4-2-3-1 vs 4-4-2

Predicted 1-0Winner: OsasunaConfidence 0.63λ home/away 1.16 / 1.12Most-likely P 11.7%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Osasuna vs Espanyol. 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 1.158, Away 1.125). Final calibrated Poisson lambdas: Home 1.158, Away 1.125 (most likely score 1-0).

Home Starters 10/11 XGBoost (9 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.16 / 1.12 Final λ (H/A) 1.16 / 1.12

FBref Team Priors: Osasuna (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 1.237) vs Espanyol (Gls/90: 1.6666666666666667, GA/90: 1.67 → E[λ]: 1.235) | 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	Osasuna	Espanyol
League position	8.00	12.00
Points per game	1.75	1.00
Attack index	1.04	1.25
Defense (concede) index	1.04	1.25
Form multiplier	1.04	0.96
Standing λ multiplier	1.04	1.19

Lambda decomposition (how the goal rates were built)

Stage	Osasuna λ	Espanyol λ
FBref Squad Prior E[λ] (weight 0.228)	1.237	1.235
Pre-competitive-floor	1.158	1.125
Pre-calibration (Micro-duels)	1.158	1.125
Final λ	1.158	1.125

Scoreline distribution & markets

Top 5 scorelines	P
1-0	11.7%
1-1	13.4%
0-1	11.3%
0-0	10.3%
2-1	7.7%

Home win	36.4%
Draw	28.7%
Away win	34.8%
Over 2.5	39.9%
BTTS yes	46.5%

Pregame fair line — favorite Osasuna (36.4%), fair total 2.28, fair spread 0.03

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.

Osasuna — 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
Alejandro Catena	D	88	0	0.00	-	n/a	0	0.0	6.7	45.7	6	XGBoost D_service
Rockson Yeboah	D	29	0	0.00	-	n/a	0	0.0	6.5	20.3	3	FBref Prior D_service
Iñigo Arguibide	D	85	0	0.02	0.00	909%	1	0.2	6.5	43.5	6	FBref Prior D_service
Sergio Herrera	G	88	0	0.00	-	n/a	0	0.0	6.7	44.8	6	FBref Prior G_service
Abel Bretones	D	88	0	0.04	0.01	564%	1	0.3	6.3	42.2	6	FBref Prior D_service
Jon Moncayola	M	79	0	0.06	0.01	329%	1	0.3	6.8	44.7	6	FBref Prior M_service
Iker Muñoz	M	73	0	0.07	0.00	1499%	0	0.2	6.8	45.2	6	FBref Prior M_service
Jonathan Dubasin	M	57	0	0.10	0.07	45%	2	0.3	6.8	36.7	7	FBref Prior M_service
Ante Budimir	F	72	1	0.54	0.68	ok	3	2.5	7.3	51.2	6	FBref Prior F_service
Romain Del Castillo	M	90	0	0.16	-	n/a	2	0.0	6.9	-	2	Prior M_service
Rubén García	M	51	0	0.07	0.06	34%	3	0.7	6.8	45.3	6	FBref Prior M_service
Team totals			1	1.16			13			6.7

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Aitor Fernández	G	4.4m	10.9%	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
Raúl Moro	M	20.3m	69.2%	Market-value substitute prior
Raúl García de Haro	F	25.3m	55.9%	Market-value substitute prior

Espanyol — 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
Roberto Fernández	F	89	0.27	0.32	ok	3	1.8	6.8	59.6	5	FBref Prior F_service
Javier Hernández	M	79	0.26	0.07	274%	2	1.0	6.7	52.4	5	FBref Prior M_service
Tyrhys Dolan	M	87	0.13	0.04	215%	2	0.8	6.9	53.0	5	FBref Prior M_service
Edu Expósito	M	82	0.13	0.09	41%	3	2.0	6.9	56.6	5	FBref Prior M_service
Gabriel Moscardo	M	52	0.05	0.01	494%	2	0.2	6.8	27.6	5	FBref Prior M_service
Álex Calatrava	M	71	0.15	0.15	ok	3	1.6	6.8	54.8	5	FBref Prior M_service
Roger Hinojo	D	87	0.00	-	n/a	0	0.0	6.6	55.2	5	FBref Prior D_service
Leandro Cabrera	D	88	0.00	-	n/a	0	0.0	6.7	34.0	2	XGBoost D_service
Unai Núñez	D	87	0.03	0.00	432%	1	0.2	6.6	54.6	5	FBref Prior D_service
Omar El Hilali	D	89	0.00	-	n/a	0	0.0	6.9	55.4	5	FBref Prior D_service
Marko Dmitrović	G	88	0.00	-	n/a	0	0.0	7.0	57.0	5	FBref Prior G_service
Team totals			1.12			16			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
Quilindschy Hartman	D	14.2m	32.5%	Market-value substitute prior
Vanja Drkušić	D	19.9m	41.2%	Market-value substitute prior
Urko González	M	22.4m	31.5%	Market-value substitute prior
Javi Puado	M	22.2m	50.8%	Market-value substitute prior
Bryan Zaragoza	F	25.5m	56.9%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Jon Moncayola vs Tyrhys Dolan will be the pivotal duel. Total antagonist xG — Home: 0.50, Away: 0.47. 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 49.5% / 50.5%, dominance ratio 0.49, key duel: Jon Moncayola vs Tyrhys Dolan

Romain Del Castillo xG 0.09Rubén García xG 0.04Jonathan Dubasin xG 0.05Roberto Fernández xG 0.21Tyrhys Dolan xG 0.11Edu Expósito xG 0.11

Summary

Antagonist matchup analysis for Osasuna vs Espanyol. Most likely scoreline: 1-0. Lambdas derived from 5 home and 4 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. Midfield is evenly contested — Jon Moncayola vs Tyrhys Dolan will be the pivotal duel. Total antagonist xG — Home: 0.50, Away: 0.47. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Tottenham vs Everton

Premier League · 20260912 · 4-2-3-1 vs 4-2-3-1

Predicted 0-1Winner: EvertonConfidence 0.61λ home/away 1.02 / 1.11Most-likely P 13.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Tottenham vs Everton. 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 1.011, Away 1.112). Final calibrated Poisson lambdas: Home 1.020, Away 1.112 (most likely score 0-1).

Home Starters 10/11 XGBoost (9 FBref) Away Starters 9/11 XGBoost (11 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.01 / 1.11 Final λ (H/A) 1.02 / 1.11

Modeling Pipeline Stages (5 layers)

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

Standing & form context

Metric	Tottenham	Everton
League position	17.00	8.00
Points per game	0.33	1.67
Attack index	1.00	1.04
Defense (concede) index	0.62	2.08
Form multiplier	0.95	1.05
Standing λ multiplier	0.82	1.39

Lambda decomposition (how the goal rates were built)

Stage	Tottenham λ	Everton λ
Pre-competitive-floor	1.011	1.112
Pre-calibration (Micro-duels)	1.011	1.112
Final λ	1.020	1.112

Scoreline distribution & markets

Top 5 scorelines	P
0-1	13.1%
1-1	13.6%
0-0	12.0%
1-0	12.0%
1-2	7.5%

Home win	32.7%
Draw	29.9%
Away win	37.4%
Over 2.5	35.9%
BTTS yes	43.0%

Pregame fair line — favorite Everton (37.4%), fair total 2.13, fair spread -0.09

Projected players vs season baseline

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

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Sávio	M	66	0.09	0.01	862%	2	0.5	7.6	37.0	2	XGBoost M_service
Sandro Tonali	M	95	0.05	0.02	101%	2	0.8	7.7	51.8	4	FBref Prior M_service
Rodrigo Bentancur	M	78	0.02	0.00	522%	1	0.2	7.1	48.2	4	FBref Prior M_service
Destiny Udogie	D	33	0.00	-	n/a	0	0.0	7.2	50.2	4	FBref Prior D_service
Micky van de Ven	D	95	0.36	0.19	87%	1	0.7	7.4	47.0	3	FBref Prior D_service
Jan Paul van Hecke	D	95	0.06	0.05	ok	3	0.8	7.7	55.2	4	FBref Prior D_service
Pedro Porro	D	95	0.02	0.12	84%	2	2.0	7.2	44.7	3	FBref Prior D_service
Antonín Kinský	G	92	0.00	-	n/a	0	0.0	7.2	48.0	4	FBref Prior G_service
Mateus Fernandes	M	54	0.03	0.00	916%	2	0.3	7.6	68.3	3	FBref Prior M_service
Mathys Tel	F	90	0.18	0.05	263%	3	1.2	7.2	46.8	4	FBref Prior F_service
Omar Marmoush	F	95	0.13	0.08	57%	3	1.2	7.4	34.8	4	XGBoost F_service
Team totals			1.02			19			7.4

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Brandon Austin	G	4.4m	10.9%	Market-value substitute prior
Marcos Senesi	D	14.4m	33.9%	Market-value substitute prior
Kevin Danso	D	14.3m	33.3%	Market-value substitute prior
Mohammed Kudus	M	23.6m	57.1%	Market-value substitute prior
Xavi Simons	M	23.4m	56.3%	Market-value substitute prior
Dominic Solanke	F	26.4m	61.0%	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
Jordan Pickford	G	92	0	0.00	-	n/a	0	0.0	6.9	42.6	5	FBref Prior G_service
Thierno Barry	F	85	1	0.22	0.46	53%	3	1.8	7.2	40.6	5	FBref Prior F_service
Jack Grealish	M	17	0	0.06	0.01	719%	2	0.3	7.2	46.0	3	FBref Prior M_service
Kiernan Dewsbury-Hall	M	95	0	0.16	0.09	79%	2	1.8	7.5	45.2	5	FBref Prior M_service
Tyrique George	F	90	0	0.28	0.04	547%	3	1.3	7.2	37.0	6	FBref Prior F_service
James Garner	M	55	0	0.04	-	n/a	1	0.0	7.5	50.5	4	FBref Prior M_service
Hayden Hackney	M	44	0	0.05	0.01	337%	2	0.5	7.4	51.5	4	FBref Prior M_service
Vitaliy Mykolenko	D	95	0	0.00	-	n/a	0	0.0	7.0	41.6	5	FBref Prior D_service
Jarrad Branthwaite	D	95	0	0.08	0.03	150%	2	0.6	7.3	41.6	5	FBref Prior D_service
James Tarkowski	D	89	0	0.05	0.03	39%	2	0.6	6.6	44.8	5	FBref Prior D_service
Merlin Röhl	M	90	0	0.09	-	n/a	1	0.0	7.1	33.8	6	FBref Prior M_service
Team totals			1	1.11			18			7.2

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
Ainsley Maitland-Niles	D	13.9m	31.6%	Market-value substitute prior
Iliman Ndiaye	M	23.5m	33.9%	Market-value substitute prior
Tim Iroegbunam	M	13.0m	70.6%	Market-value substitute prior
Brennan Johnson	F	21.8m	74.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Sandro Tonali vs James Garner will be the pivotal duel. Total antagonist xG — Home: 0.48, Away: 0.58. 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 50.7% / 49.3%, dominance ratio 0.51, key duel: Sandro Tonali vs James Garner

Mateus Fernandes xG 0.06Sávio xG 0.11Omar Marmoush xG 0.23Kiernan Dewsbury-Hall xG 0.19Hayden Hackney xG 0.06Jack Grealish xG 0.04

Summary

Antagonist matchup analysis for Tottenham vs Everton. Most likely scoreline: 0-1. Lambdas derived from 4 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 — Sandro Tonali vs James Garner will be the pivotal duel. Total antagonist xG — Home: 0.48, Away: 0.58. 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 Fulham

Premier League · 20260912 · 4-2-3-1 vs 4-2-3-1

Predicted 2-0Winner: LiverpoolConfidence 0.73λ home/away 2.67 / 0.95Most-likely P 9.5%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Liverpool 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 2.424, Away 0.981). Final calibrated Poisson lambdas: Home 2.665, Away 0.954 (most likely score 2-0).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (11 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 2.42 / 0.98 Final λ (H/A) 2.67 / 0.95

FBref Team Priors: Liverpool FC (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 1.481) vs Fulham (Gls/90: 1.0, GA/90: 1.0 → E[λ]: 1.481) | 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	Fulham
League position	6.00	19.00
Points per game	1.67	0.00
Attack index	2.50	0.83
Defense (concede) index	1.46	1.67
Form multiplier	1.06	0.94
Standing λ multiplier	1.65	1.13

Lambda decomposition (how the goal rates were built)

Stage	Liverpool λ	Fulham λ
FBref Squad Prior E[λ] (weight 0.192)	1.481	1.481
Pre-mismatch	2.424	0.981
Pre-calibration (Micro-duels)	2.424	0.981
Final λ	2.665	0.954

Scoreline distribution & markets

Top 5 scorelines	P
2-0	9.5%
2-1	9.1%
3-0	8.5%
3-1	8.1%
1-0	7.1%

Home win	73.6%
Draw	15.3%
Away win	11.0%
Over 2.5	70.0%
BTTS yes	57.2%

Pregame fair line — favorite Liverpool (73.6%), fair total 3.62, fair spread 1.71

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
Alexander Isak	F	91	1	0.70	0.46	54%	3	1.8	8.3	45.8	5	FBref Prior F_service
Bradley Barcola	F	29	0	0.28	-	n/a	1	0.0	7.6	33.0	2	XGBoost F_service
Florian Wirtz	M	90	0	0.32	0.13	146%	1	1.4	7.8	38.6	5	FBref Prior M_service
Víctor Muñoz	F	29	0	0.27	0.07	291%	2	1.0	7.2	35.0	6	FBref Prior F_service
Alexis Mac Allister	M	70	0	0.08	0.02	384%	2	0.4	7.7	41.8	5	FBref Prior M_service
Dominik Szoboszlai	M	95	1	0.23	0.23	ok	4	1.8	7.7	43.4	5	FBref Prior M_service
Miloš Kerkez	D	90	0	0.04	0.00	702%	2	0.4	7.1	38.6	5	FBref Prior D_service
Virgil van Dijk	D	92	0	0.46	0.05	831%	1	0.4	7.2	43.8	5	FBref Prior D_service
Jérémy Jacquet	D	87	0	0.00	-	n/a	0	0.0	7.6	45.4	5	FBref Prior D_service
Ronald Araújo	D	43	0	0.00	-	n/a	0	0.0	6.7	43.4	5	FBref Prior D_service
Alisson	G	93	0	0.00	-	n/a	0	0.0	7.2	41.8	5	FBref Prior G_service
Team totals			2	2.67			17			7.5

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
Giovanni Leoni	D	14.6m	34.5%	Market-value substitute prior
Ryan Gravenberch	M	23.8m	58.0%	Market-value substitute prior
Cody Gakpo	M	23.6m	57.3%	Market-value substitute prior
Hugo Ekitiké	F	27.0m	63.8%	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
Bernd Leno	G	89	0.00	-	n/a	0	0.0	6.7	46.8	4	FBref Prior G_service
Timothy Castagne	D	83	0.23	0.17	38%	3	1.0	6.7	49.2	4	FBref Prior D_service
Calvin Bassey	D	95	0.01	0.00	248%	0	0.2	7.4	49.8	4	FBref Prior D_service
Gonzalo García	F	95	0.13	0.36	65%	3	2.8	7.3	49.8	4	FBref Prior F_service
César Palacios	M	70	0.09	0.24	63%	3	2.0	6.8	48.0	4	FBref Prior M_service
Joshua King	M	95	0.13	0.24	46%	3	1.8	7.4	52.5	4	FBref Prior M_service
Oscar Bobb	M	75	0.13	0.08	59%	2	0.8	7.4	51.8	4	FBref Prior M_service
Alex Iwobi	M	91	0.05	0.01	256%	1	0.5	7.3	53.5	4	FBref Prior M_service
Shea Charles	M	42	0.04	0.02	57%	1	0.5	7.1	49.8	4	FBref Prior M_service
Antonee Robinson	D	88	0.08	0.05	50%	1	0.8	7.0	47.8	4	FBref Prior D_service
Joachim Andersen	D	94	0.00	-	n/a	0	0.0	7.2	46.3	3	FBref Prior D_service
Team totals			0.95			18			7.1

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
Ryan Sessegnon	D	18.0m	61.8%	Market-value substitute prior
David Affengruber	D	14.3m	33.0%	Market-value substitute prior
Hugo Larsson	M	23.1m	54.9%	Market-value substitute prior
Sander Berge	M	23.0m	32.7%	Market-value substitute prior
Rodrigo Muniz	F	16.7m	73.6%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~53% possession expected (Florian Wirtz vs Oscar Bobb). Total antagonist xG — Home: 0.75, Away: 0.67. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Right Wing vs Left Back — Flank Battle.

Midfield — possession 52.6% / 47.4%, dominance ratio 0.57, key duel: Florian Wirtz vs Oscar Bobb

Dominik Szoboszlai xG 0.16Alexander Isak xG 0.39Florian Wirtz xG 0.20César Palacios xG 0.12Oscar Bobb xG 0.19Joshua King xG 0.12

Summary

Antagonist matchup analysis for Liverpool vs Fulham. Most likely scoreline: 2-0. Lambdas derived from 3 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. Home midfield dominates with ~53% possession expected (Florian Wirtz vs Oscar Bobb). Total antagonist xG — Home: 0.75, Away: 0.67. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Right Wing vs Left Back — Flank Battle.

Chelsea vs Hull

Premier League · 20260912 · 3-4-2-1 vs 5-4-1

Predicted 3-1Winner: ChelseaConfidence 0.75λ home/away 3.82 / 1.22Most-likely P 7.4%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Chelsea vs Hull. 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 3.242, Away 1.292). Final calibrated Poisson lambdas: Home 3.821, Away 1.215 (most likely score 3-1).

Home Starters 8/11 XGBoost (10 FBref) Away Starters 11/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 3.24 / 1.29 Final λ (H/A) 3.82 / 1.22

FBref Team Priors: Chelsea (Gls/90: 3.5, GA/90: 3.5 → E[λ]: 3.5) vs Hull City (Gls/90: 1.5, GA/90: 1.5 → 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	Chelsea	Hull
League position	4.00	3.00
Points per game	2.00	2.33
Attack index	3.33	0.62
Defense (concede) index	1.00	2.92
Form multiplier	0.98	1.02
Standing λ multiplier	1.64	1.28

Lambda decomposition (how the goal rates were built)

Stage	Chelsea λ	Hull λ
FBref Squad Prior E[λ] (weight 0.192)	3.500	3.500
Pre-mismatch	3.242	1.292
Pre-calibration (Micro-duels)	3.242	1.292
Final λ	3.821	1.215

Scoreline distribution & markets

Top 5 scorelines	P
3-1	7.4%
4-1	7.1%
3-0	6.1%
4-0	5.8%
2-1	5.8%

Home win	83.0%
Draw	9.7%
Away win	7.3%
Over 2.5	87.8%
BTTS yes	68.8%

Pregame fair line — favorite Chelsea (83.0%), fair total 5.04, fair spread 2.61

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
João Pedro	F	95	2	1.41	0.47	201%	3	2.5	7.8	56.8	4	FBref Prior F_service
Morgan Rogers	M	90	0	0.59	0.23	153%	2	1.8	7.5	47.2	5	FBref Prior M_service
Cole Palmer	M	90	0	0.59	0.21	181%	2	2.4	7.5	46.6	5	FBref Prior M_service
Jorrel Hato	D	90	0	0.10	0.00	3554%	1	0.2	7.3	41.2	5	FBref Prior D_service
Reece James	D	24	0	0.00	0.04	100%	0	1.2	7.3	50.0	4	FBref Prior D_service
Roméo Lavia	M	67	0	0.19	0.19	ok	1	0.5	7.1	53.0	4	FBref Prior M_service
Pedro Neto	M	82	1	0.73	0.12	533%	3	1.0	7.7	53.8	4	FBref Prior M_service
Wesley Fofana	D	84	0	0.00	-	n/a	0	0.0	7.0	45.3	3	FBref Prior D_service
Maxence Lacroix	D	95	0	0.09	0.01	1622%	1	0.2	7.4	50.2	4	FBref Prior D_service
Josh Acheampong	D	71	0	0.00	-	n/a	0	0.0	7.0	47.7	4	XGBoost D_service
Emiliano Martínez	G	91	0	0.00	-	n/a	0	0.0	7.3	55.0	3	FBref Prior G_service
Team totals			3	3.82			13			7.4

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
Levi Colwill	D	15.2m	25.0%	Market-value substitute prior
Malo Gusto	D	14.8m	24.3%	Market-value substitute prior
Moisés Caicedo	M	18.4m	72.9%	Market-value substitute prior
Enzo Fernández	M	25.0m	72.9%	Market-value substitute prior
Emmanuel Emegha	F	26.3m	60.3%	Market-value substitute prior

Hull — 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
Oli McBurnie	F	89	1	0.19	0.13	45%	4	1.2	6.7	50.5	4	XGBoost F_service
Elliot Stroud	M	64	0	0.08	0.01	452%	1	0.5	6.7	49.3	4	FBref Prior M_service
Lucas Gourna-Douath	M	63	0	0.03	-	n/a	1	0.0	6.7	34.2	4	FBref Prior M_service
Regan Slater	M	89	0	0.05	0.01	571%	2	0.4	6.8	41.6	5	FBref Prior M_service
Mohamed Belloumi	M	84	0	0.10	0.05	101%	2	1.2	6.7	51.2	4	XGBoost M_service
Ryan Giles	D	89	0	0.02	0.00	374%	0	0.2	6.8	43.2	5	FBref Prior D_service
John Egan	D	88	0	0.00	-	n/a	0	0.0	6.6	44.0	5	FBref Prior D_service
Semi Ajayi	D	80	0	0.50	0.10	380%	1	0.2	6.6	43.2	5	FBref Prior D_service
Nobel Mendy	D	65	0	0.10	0.06	56%	2	0.8	6.7	44.6	5	FBref Prior D_service
Lewie Coyle	D	59	0	0.00	-	n/a	0	0.0	6.7	41.2	5	FBref Prior D_service
Konstantinos Tzolakis	G	93	0	0.00	-	n/a		0.0	7.5	47.2	5	XGBoost G_service
Team totals			1	1.22			14			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

Antagonist / tactical summary

Home midfield dominates with ~53% possession expected (Morgan Rogers vs Elliot Stroud). Total antagonist xG — Home: 0.98, Away: 0.47. Home danger zone: Shadow Striker vs Centre Back — Half-Space Threat. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 53.1% / 46.9%, dominance ratio 0.63, key duel: Morgan Rogers vs Elliot Stroud

Roméo Lavia xG 0.06Morgan Rogers xG 0.18Cole Palmer xG 0.18Ryan Giles xG 0.02Lewie Coyle xG 0.06Regan Slater xG 0.04

Summary

Antagonist matchup analysis for Chelsea vs Hull. Most likely scoreline: 3-1. Lambdas derived from 5 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 ~53% possession expected (Morgan Rogers vs Elliot Stroud). Total antagonist xG — Home: 0.98, Away: 0.47. Home danger zone: Shadow Striker vs Centre Back — Half-Space Threat. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Crystal Palace vs Ipswich

Premier League · 20260912 · 3-4-2-1 vs 4-2-3-1

Predicted 2-1Winner: Crystal PalaceConfidence 0.64λ home/away 1.70 / 1.37Most-likely P 9.2%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Crystal Palace vs Ipswich. 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 1.698, Away 1.374). Final calibrated Poisson lambdas: Home 1.698, Away 1.374 (most likely score 2-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 10/11 XGBoost (11 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.70 / 1.37 Final λ (H/A) 1.70 / 1.37

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	Ipswich
League position	14.00	13.00
Points per game	1.00	1.00
Attack index	1.67	0.83
Defense (concede) index	1.67	3.33
Form multiplier	1.00	1.00
Standing λ multiplier	1.53	1.53

Lambda decomposition (how the goal rates were built)

Stage	Crystal Palace λ	Ipswich λ
Pre-competitive-floor	1.698	1.374
Pre-calibration (Micro-duels)	1.698	1.374
Final λ	1.698	1.374

Scoreline distribution & markets

Top 5 scorelines	P
2-1	9.2%
1-1	10.9%
1-0	7.8%
1-2	7.4%
2-0	6.7%

Home win	45.1%
Draw	23.8%
Away win	31.1%
Over 2.5	59.3%
BTTS yes	61.1%

Pregame fair line — favorite Crystal Palace (45.1%), fair total 3.07, fair spread 0.32

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
Dean Henderson	G	95	0	0.00	-	n/a	0	0.0	7.4	51.0	4	FBref Prior G_service
Chris Richards	D	95	0	0.06	0.02	218%	1	0.5	7.2	49.8	4	FBref Prior D_service
Jørgen Strand Larsen	F	49	0	0.27	0.10	171%	2	0.7	7.2	68.0	3	FBref Prior F_service
Daichi Kamada	M	91	0	0.10	0.01	776%	1	0.2	7.0	52.7	4	FBref Prior M_service
Yéremy Pino	F	83	1	0.41	0.09	355%	2	1.0	7.1	51.5	4	FBref Prior F_service
Tyrick Mitchell	M	89	1	0.19	0.19	ok	4	1.2	7.2	54.5	4	FBref Prior M_service
Quinten Timber	M	78	0	0.10	0.01	962%	1	0.5	7.1	32.5	2	XGBoost M_service
Adam Wharton	M	95	0	0.11	-	n/a	2	0.0	7.7	52.5	4	FBref Prior M_service
Anan Khalaili	M	87	0	0.16	0.18	ok	2	0.8	7.2	55.5	4	FBref Prior M_service
Jaydee Canvot	D	95	0	0.08	0.01	558%	0	0.2	7.0	48.0	4	FBref Prior D_service
Axel Disasi	D	54	0	0.00	-	n/a	0	0.0	6.9	47.3	3	FBref Prior D_service
Team totals			2	1.70			16			7.2

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Walter Benítez	G	4.4m	11.0%	Market-value substitute prior
Honest Ahanor	D	14.7m	35.0%	Market-value substitute prior
Daniel Muñoz	D	14.4m	23.5%	Market-value substitute prior
Dwight McNeil	M	22.9m	51.4%	Market-value substitute prior
Óscar Mingueza	M	19.0m	70.7%	Market-value substitute prior
Ismaïla Sarr	F	26.7m	62.3%	Market-value substitute prior

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	59	1	0.15	0.26	42%	2	1.0	6.8	52.0	4	FBref Prior F_service
Daizen Maeda	F	90	0	0.19	0.14	32%	2	0.6	7.0	36.8	5	FBref Prior F_service
Julio Enciso	M	88	0	0.23	0.22	ok	4	3.0	7.2	52.8	4	FBref Prior M_service
Abdul Fatawu Issahaku	M	79	0	0.10	0.01	1270%	2	0.5	7.0	52.8	4	FBref Prior M_service
Exequiel Palacios	M	56	0	0.05	-	n/a	0	0.0	7.3	47.0	3	FBref Prior M_service
Saša Lukić	M	85	0	0.06	0.00	1246%	0	0.2	6.9	49.2	4	FBref Prior M_service
Leif Davis	D	94	0	0.37	0.16	129%	3	0.8	6.8	50.0	4	FBref Prior D_service
Jacob Greaves	D	92	0	0.00	-	n/a	0	0.0	6.7	45.8	4	FBref Prior D_service
Issa Diop	D	90	0	0.00	-	n/a	0	0.0	6.8	49.5	4	FBref Prior D_service
Dara O'Shea	D	93	0	0.08	0.02	317%	1	0.2	6.8	46.5	4	FBref Prior D_service
Kjell Scherpen	G	90	0	0.00	-	n/a	0	0.0	7.2	56.0	4	FBref Prior G_service
Team totals			1	1.37			15			7.0

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Christian Walton	G	4.4m	10.9%	Market-value substitute prior
Darnell Furlong	D	16.0m	60.2%	Market-value substitute prior
Cédric Kipré	D	13.6m	29.9%	Market-value substitute prior
Jack Clarke	M	21.2m	70.8%	Market-value substitute prior
Jaden Philogene-Bidace	M	22.7m	53.1%	Market-value substitute prior
Anis Mehmeti	F	25.8m	58.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Adam Wharton vs Exequiel Palacios will be the pivotal duel. Total antagonist xG — Home: 0.45, Away: 0.57. Home danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 51.0% / 49.0%, dominance ratio 0.53, key duel: Adam Wharton vs Exequiel Palacios

Jørgen Strand Larsen xG 0.18Daichi Kamada xG 0.06Tyrick Mitchell xG 0.12Abdul Fatawu Issahaku xG 0.09Julio Enciso xG 0.17Emersonn xG 0.14

Summary

Antagonist matchup analysis for Crystal Palace vs Ipswich. Most likely scoreline: 2-1. Lambdas derived from 4 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. Midfield is evenly contested — Adam Wharton vs Exequiel Palacios will be the pivotal duel. Total antagonist xG — Home: 0.45, Away: 0.57. Home danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Aston Villa vs Forest

Premier League · 20260912 · 4-2-3-1 vs 3-4-2-1

Predicted 1-1Winner: DrawConfidence 0.61λ home/away 1.02 / 0.98Most-likely P 13.7%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Aston Villa vs Forest. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 3-4-2-1 (duel lambdas: Home 0.976, Away 0.983). Final calibrated Poisson lambdas: Home 1.020, Away 0.983 (most likely score 1-1).

Home Starters 11/11 XGBoost (10 FBref) Away Starters 8/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.98 / 0.98 Final λ (H/A) 1.02 / 0.98

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	Forest
League position	18.00	16.00
Points per game	0.33	0.67
Attack index	1.00	0.42
Defense (concede) index	0.62	2.08
Form multiplier	0.98	1.02
Standing λ multiplier	0.83	0.95

Lambda decomposition (how the goal rates were built)

Stage	Aston Villa λ	Forest λ
Pre-competitive-floor	0.976	0.983
Pre-calibration (Micro-duels)	0.976	0.983
Final λ	1.020	0.983

Scoreline distribution & markets

Top 5 scorelines	P
1-1	13.7%
1-0	13.6%
0-0	13.6%
0-1	13.1%
2-0	7.0%

Home win	35.4%
Draw	31.1%
Away win	33.5%
Over 2.5	32.4%
BTTS yes	40.2%

Pregame fair line — favorite Aston Villa (35.4%), fair total 2.00, fair spread 0.04

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	84	1	0.21	0.08	167%	2	0.7	7.1	45.3	3	FBref Prior F_service
George Hemmings	M	77	0	0.07	0.02	323%	1	0.2	6.7	47.8	4	FBref Prior M_service
John McGinn	M	89	0	0.16	0.19	ok	2	1.0	6.7	46.0	4	FBref Prior M_service
Ross Barkley	M	79	0	0.07	0.09	ok	2	1.5	6.9	51.2	4	FBref Prior M_service
Boubacar Kamara	M	95	0	0.05	-	n/a	2	0.0	7.5	50.0	4	FBref Prior M_service
Ian Maatsen	D	87	0	0.05	0.02	102%	2	0.8	7.1	46.0	4	FBref Prior D_service
Pau Torres	D	85	0	0.00	-	n/a	0	0.0	6.9	38.0	3	FBref Prior D_service
Victor Lindelöf	D	89	0	0.00	-	n/a	0	0.0	6.7	49.2	4	FBref Prior D_service
Matty Cash	D	88	0	0.15	0.04	299%	0	0.2	6.8	49.5	4	FBref Prior D_service
Zion Suzuki	G	95	0	0.00	-	n/a	0	0.0	7.8	35.8	4	FBref Prior G_service
Emiliano Buendía	M	84	0	0.15	0.20	ok	2	1.5	7.0	47.8	4	XGBoost M_service
Team totals			1	1.02			14			7.0

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
Matteo Ruggeri	D	11.5m	62.3%	Market-value substitute prior
Taylor Harwood-Bellis	D	14.4m	33.7%	Market-value substitute prior
Johan Manzambi	M	23.7m	57.7%	Market-value substitute prior
Amadou Onana	M	23.4m	56.1%	Market-value substitute prior
Ibrahim Mbaye	F	26.4m	60.8%	Market-value substitute prior

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Dan Ndoye	M	90	0	0.10	0.09	ok	2	0.8	7.3	51.2	4	FBref Prior M_service
Neco Williams	D	90	0	0.02	0.03	41%	0	0.2	7.2	55.5	4	FBref Prior D_service
James McAtee	M	87	0	0.08	0.03	165%	2	0.8	7.1	52.8	4	FBref Prior M_service
Xaver Schlager	M	66	0	0.04	0.02	120%	1	0.8	6.8	51.5	4	FBref Prior M_service
Daniel Muñoz	M	58	0	0.09	0.09	ok	2	1.0	7.1	42.0	3	FBref Prior M_service
Nikola Milenković	D	95	0	0.10	0.03	246%	2	0.5	7.2	50.5	4	FBref Prior D_service
Murillo	D	95	0	0.16	0.09	79%	2	0.8	7.3	51.0	4	FBref Prior D_service
Jair	D	92	0	0.03	0.01	306%	1	0.2	6.9	51.5	4	XGBoost D_service
Matz Sels	G	89	0	0.00	-	n/a	0	0.0	6.9	49.5	4	FBref Prior G_service
Morgan Gibbs-White	M	90	0	0.12	0.35	66%	2	1.8	7.5	53.0	4	FBref Prior M_service
Liam Delap	F	52	1	0.14	0.04	222%	2	0.7	7.2	43.3	3	FBref Prior F_service
Team totals			1	0.98			17			7.1

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
Ousmane Diomande	D	15.0m	36.4%	Market-value substitute prior
Ola Aina	D	14.2m	32.7%	Market-value substitute prior
Callum Hudson Odoi	M	23.1m	55.2%	Market-value substitute prior
Ibrahim Sangaré	M	22.8m	53.5%	Market-value substitute prior
Igor Jesus	F	26.3m	60.3%	Market-value substitute prior

Antagonist / tactical summary

Midfield is evenly contested — Boubacar Kamara vs Morgan Gibbs-White will be the pivotal duel. Total antagonist xG — Home: 0.54, Away: 0.50. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Central Mid vs Defensive Mid — Pressing/Creation Duel.

Midfield — possession 48.9% / 51.1%, dominance ratio 0.46, key duel: Boubacar Kamara vs Morgan Gibbs-White

John McGinn xG 0.13Boubacar Kamara xG 0.06Emiliano Buendía xG 0.12Liam Delap xG 0.17James McAtee xG 0.10Xaver Schlager xG 0.04

Summary

Antagonist matchup analysis for Aston Villa vs Forest. Most likely scoreline: 1-1. Lambdas derived from 4 home and 4 away individual player duels.

Tactical parity between 4-2-3-1 and 3-4-2-1. Match outcome driven primarily by individual player quality. Midfield is evenly contested — Boubacar Kamara vs Morgan Gibbs-White will be the pivotal duel. Total antagonist xG — Home: 0.54, Away: 0.50. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Central Mid vs Defensive Mid — Pressing/Creation Duel.

Real Madrid vs Rayo Vallecano

LaLiga · 20260912 · 4-2-3-1 vs 4-3-3

Predicted 4-1Winner: Real MadridConfidence 0.77λ home/away 4.29 / 1.21Most-likely P 7.1%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Real Madrid vs Rayo Vallecano. Player statistics regressed using position-specific XGBoost models (G, D, M, F) with 2026-2027 FBref priors. Micro-duels resolved across 4-2-3-1 vs 4-3-3 (duel lambdas: Home 3.529, Away 1.301). Final calibrated Poisson lambdas: Home 4.289, Away 1.205 (most likely score 4-1).

Home Starters 10/11 XGBoost (11 FBref) Away Starters 10/11 XGBoost (8 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 3.53 / 1.30 Final λ (H/A) 4.29 / 1.21

FBref Team Priors: Real Madrid (Gls/90: 3.0, GA/90: 3.33 → E[λ]: 2.956) vs Rayo Vallecano (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	Rayo Vallecano
League position	3.00	14.00
Points per game	2.25	1.00
Attack index	2.08	1.46
Defense (concede) index	2.08	0.62
Form multiplier	1.05	0.95
Standing λ multiplier	1.65	0.95

Lambda decomposition (how the goal rates were built)

Stage	Real Madrid λ	Rayo Vallecano λ
FBref Squad Prior E[λ] (weight 0.228)	2.956	3.289
Pre-mismatch	3.529	1.301
Pre-calibration (Micro-duels)	3.529	1.301
Final λ	4.289	1.205

Scoreline distribution & markets

Top 5 scorelines	P
4-1	7.1%
3-1	6.6%
5-1	6.1%
4-0	5.9%
3-0	5.5%

Home win	87.1%
Draw	7.6%
Away win	5.3%
Over 2.5	91.0%
BTTS yes	69.1%

Pregame fair line — favorite Real Madrid (87.1%), fair total 5.49, fair spread 3.08

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.

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	95	3	1.58	0.86	85%	5	4.4	8.5	45.0	7	FBref Prior F_service
Vinícius Júnior	F	90	1	0.93	0.27	246%	4	1.4	7.5	36.5	8	FBref Prior F_service
Jude Bellingham	M	94	0	0.32	0.12	166%	5	1.6	7.9	46.7	7	FBref Prior M_service
Arda Güler	M	59	0	0.18	0.16	ok	3	0.9	7.7	43.4	7	FBref Prior M_service
Eduardo Camavinga	M	48	0	0.09	-	n/a	1	0.0	7.5	38.7	7	FBref Prior M_service
Bernardo Silva	M	53	0	0.09	-	n/a	0	0.0	7.2	37.6	7	FBref Prior M_service
Álvaro Carreras	D	44	0	0.00	-	n/a	0	0.0	7.2	28.4	7	FBref Prior D_service
Dean Huijsen	D	95	0	0.46	0.08	500%	3	0.7	7.7	41.6	7	FBref Prior D_service
Antonio Rüdiger	D	89	0	0.11	0.01	1476%	1	0.1	6.8	10.7	7	FBref Prior D_service
Trent Alexander-Arnold	D	46	0	0.23	0.01	1692%	2	0.3	7.3	30.6	7	FBref Prior D_service
Thibaut Courtois	G	92	0	0.00	-	n/a	0	0.0	7.1	38.0	7	FBref Prior G_service
Team totals			4	4.29			25			7.5

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
Marc Cucurella	D	26.6m	50.8%	Market-value substitute prior
Ibrahima Konaté	D	15.0m	24.7%	Market-value substitute prior
Federico Valverde	M	23.8m	34.3%	Market-value substitute prior
Aurélien Tchouaméni	M	23.7m	57.7%	Market-value substitute prior
Yan Diomande	F	23.2m	75.6%	Market-value substitute prior

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

Player	Pos	Min	Proj G	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Florian Lejeune	D	88	0	0.05	0.02	151%	3	1.0	6.7	43.3	6	FBref Prior D_service
Andrei Rațiu	D	93	0	0.22	0.08	173%	3	0.8	6.9	32.8	6	FBref Prior D_service
Emil Audero	G	90	0	0.00	-	n/a		0.0	6.8	-	3	Prior G_service
Pathé Ismaël Ciss	M	88	0	0.04	0.01	349%	1	0.2	6.7	43.7	6	XGBoost M_service
Adrià Pedrosa	D	65	0	0.08	0.02	429%	2	0.5	6.6	31.2	4	FBref Prior D_service
Unai López	M	82	0	0.07	0.02	367%	1	0.3	6.8	46.8	6	FBref Prior M_service
Álvaro García	M	64	0	0.08	0.18	57%	2	0.7	6.5	43.7	6	FBref Prior M_service
Sergio Camello	F	61	1	0.38	0.30	ok	2	1.7	7.5	52.7	6	FBref Prior F_service
Pedro Díaz	M	44	0	0.06	0.01	494%	1	0.3	6.7	33.5	6	FBref Prior M_service
Gnangoro Bouaré	M	44	0	0.05	0.01	357%	1	0.2	6.6	32.8	4	XGBoost M_service
Óscar Valentín	M	64	0	0.04	-	n/a	0	0.0	6.7	43.8	6	FBref Prior M_service
Team totals			1	1.21			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
Mujaid Sadick	D	13.7m	30.3%	Market-value substitute prior
Marash Kumbulla	D	13.6m	29.9%	Market-value substitute prior
Isi Palazón	M	22.0m	49.9%	Market-value substitute prior
Giorgi Tsitaishvili	M	22.0m	49.9%	Market-value substitute prior
Jorge de Frutos	F	25.7m	57.6%	Market-value substitute prior

Antagonist / tactical summary

Home midfield dominates with ~54% possession expected (Jude Bellingham vs Pedro Díaz). Total antagonist xG — Home: 1.02, Away: 0.34. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Midfield — possession 54.1% / 45.9%, dominance ratio 0.63, key duel: Jude Bellingham vs Pedro Díaz

Arda Güler xG 0.09Jude Bellingham xG 0.19Kylian Mbappé xG 0.69Sergio Camello xG 0.28Pathé Ismaël Ciss xG 0.02Unai López xG 0.04

Summary

Antagonist matchup analysis for Real Madrid vs Rayo Vallecano. Most likely scoreline: 4-1. Lambdas derived from 4 home and 3 away individual player duels.

Tactical parity between 4-2-3-1 and 4-3-3. Match outcome driven primarily by individual player quality. Home midfield dominates with ~54% possession expected (Jude Bellingham vs Pedro Díaz). Total antagonist xG — Home: 1.02, Away: 0.34. Home danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle. Away danger zone: Left Wing vs Right Back — Flank Battle.

Generated 2026-09-12 13:33:18 UTC · Soccer prediction reporting