Soccer predictions: actual data vs predicted data

Slate 20261012 · 2 match(es)

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

All matches overview

Match	Score	Winner	H / D / A	O2.5	BTTS	Conf	λ H/A	Actual	Result
Coventry vs Newcastle Premier League	0-1	Newcastle	18.3% / 24.9% / 56.8%	43.5%	44.2%	0.73	0.80 / 1.62	-	pending
Levante vs Sevilla LaLiga	1-2	Sevilla	35.8% / 24.2% / 40.0%	58.6%	61.1%	0.7	1.47 / 1.57	-	pending

Match detail

Coventry vs Newcastle

Premier League · 20261012 · 3-4-2-1 vs 4-2-3-1

Predicted 0-1Winner: NewcastleConfidence 0.73λ home/away 0.80 / 1.62Most-likely P 14.3%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Coventry vs Newcastle. 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 0.842, Away 1.542). Final calibrated Poisson lambdas: Home 0.800, Away 1.619 (most likely score 0-1).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (10 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 0.84 / 1.54 Final λ (H/A) 0.80 / 1.62

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	Coventry	Newcastle
League position	19.00	11.00
Points per game	1.00	1.46
Attack index	0.79	1.01
Defense (concede) index	1.01	1.19
Form multiplier	0.97	1.03
Standing λ multiplier	0.91	1.08

Lambda decomposition (how the goal rates were built)

Stage	Coventry λ	Newcastle λ
Pre-competitive-floor	0.800	1.619
Pre-calibration (Micro-duels)	0.842	1.542
Final λ	0.800	1.619

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

Scoreline distribution & markets

Top 5 scorelines	P
0-1	14.3%
0-2	11.7%
1-1	11.6%
1-2	9.3%
0-0	9.0%

Home win	18.3%
Draw	24.9%
Away win	56.8%
Over 2.5	43.5%
BTTS yes	44.2%

Pregame fair line — favorite Newcastle (56.8%), fair total 2.42, fair spread -0.82

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.

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

Player	Pos	Min	Proj xG	Season xG/g		Proj Sh	Season Sh/g	Proj Rtg	Season Rtg	Rec	Model / FBref Prior
Ethan Pinnock	D	87	0.02	0.00	361%	1	0.1	6.7	11.2	31	XGBoost D_service
Brandon Thomas-Asante	F	80	0.09	0.03	228%	1	0.4	6.6	32.4	12	FBref Prior F_service
Ephron Mason-Clark	F	65	0.16	0.03	442%	1	0.2	6.7	18.8	17	FBref Prior F_service
Jack Rudoni	M	76	0.13	0.12	ok	2	0.7	6.9	40.9	14	XGBoost M_service
Jay DaSilva	D	89	0.11	0.06	85%	1	0.4	6.7	39.6	14	FBref Prior D_service
Matt Grimes	M	88	0.04	0.01	261%	1	0.4	6.9	31.2	11	FBref Prior M_service
Frank Onyeka	M	82	0.03	0.00	921%	0	0.1	6.7	26.2	10	FBref Prior M_service
Milan van Ewijk	D	90	0.00	-	n/a	0	0.0	6.7	30.8	13	FBref Prior D_service
Stephen Mfuni	D	90	0.00	-	n/a	1	0.0	6.7	6.6	11	XGBoost D_service
Bobby Thomas	D	89	0.10	0.04	123%	1	0.9	6.9	33.0	11	FBref Prior D_service
Carl Rushworth	G	90	0.00	-	n/a		0.0	7.1	30.7	11	FBref Prior G_service
Team totals			0.80			11			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Daniel Bentley	G	4.4m	10.9%	Market-value substitute prior
Liam Kitching	D	14.1m	32.5%	Market-value substitute prior
Aurèle Amenda	D	13.9m	22.4%	Market-value substitute prior
Caleb Yirenkyi	M	22.7m	32.2%	Market-value substitute prior
Victor Torp	M	23.9m	70.3%	Market-value substitute prior
Sidiki Cherif	F	25.9m	58.8%	Market-value substitute prior

Newcastle — 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
Yoane Wissa	F	83	1	0.44	0.19	128%	2	0.8	6.7	41.7	32	FBref Prior F_service
Harvey Barnes	F	85	0	0.23	0.13	72%	2	1.5	6.8	56.7	35	FBref Prior F_service
Joe Willock	M	76	0	0.26	0.07	287%	2	0.9	6.9	43.7	29	FBref Prior M_service
Jacob Murphy	F	70	0	0.12	0.01	895%	1	0.4	6.7	54.1	33	FBref Prior F_service
Lewis Miley	M	84	0	0.06	0.03	66%	0	0.2	6.9	46.4	21	FBref Prior M_service
Nico González	M	69	0	0.05	0.01	624%	1	0.1	6.9	29.7	25	XGBoost M_service
Lewis Hall	D	88	0	0.08	0.03	178%	1	0.6	6.9	51.0	30	FBref Prior D_service
Sven Botman	D	89	0	0.05	0.06	ok	1	0.5	6.9	46.1	29	FBref Prior D_service
Malick Thiaw	D	90	0	0.10	0.11	ok	0	0.5	6.8	55.0	30	FBref Prior D_service
Amar Dedić	D	83	0	0.05	0.01	296%	1	0.3	6.8	23.5	11	FBref Prior D_service
Lukáš Horníček	G	90	0	0.00	-	n/a		0.0	6.9	33.6	11	FBref Prior G_service
Team totals			1	1.62			12			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Ewen Jaouen	G	4.8m	13.0%	Market-value substitute prior
Tino Livramento	D	15.0m	36.4%	Market-value substitute prior
Dan Burn	D	13.6m	30.1%	Market-value substitute prior
Joelinton	M	23.0m	54.5%	Market-value substitute prior
Aladji Bamba	M	18.4m	70.5%	Market-value substitute prior
Nick Woltemade	F	23.1m	75.2%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~52% possession expected (Jack Rudoni vs Nico González). Total antagonist xG — Home: 0.48, Away: 0.74. 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 47.8% / 52.2%, dominance ratio 0.44, key duel: Jack Rudoni vs Nico González

Brandon Thomas-Asante xG 0.10Ephron Mason-Clark xG 0.17Matt Grimes xG 0.04Joe Willock xG 0.18Harvey Barnes xG 0.16Yoane Wissa xG 0.31

Summary

Antagonist matchup analysis for Coventry vs Newcastle. Most likely scoreline: 0-1. Lambdas derived from 5 home and 4 away individual player duels. Head-to-head: Coventry 1W-1D-8L vs Newcastle over 10 meetings.

Tactical parity between 3-4-2-1 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~52% possession expected (Jack Rudoni vs Nico González). Total antagonist xG — Home: 0.48, Away: 0.74. Home danger zone: Shadow Striker vs CDM + CB — Zone 14 Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Levante vs Sevilla

LaLiga · 20261012 · 4-3-3 vs 4-2-3-1

Predicted 1-2Winner: SevillaConfidence 0.7λ home/away 1.47 / 1.57Most-likely P 8.7%

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

XGBoost Reasoning & FBref Dataset Tracing

Antagonist + XGBoost match analysis for Levante vs Sevilla. 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 1.527, Away 1.515). Final calibrated Poisson lambdas: Home 1.472, Away 1.569 (most likely score 1-2).

Home Starters 11/11 XGBoost (8 FBref) Away Starters 11/11 XGBoost (6 FBref) Bench Modeled H: 7 / A: 7 Duel λ (H/A) 1.53 / 1.51 Final λ (H/A) 1.47 / 1.57

FBref Team Priors: Levante UD (Gls/90: 1.6666666666666667, GA/90: 1.67 → E[λ]: 2.469) vs Sevilla (Gls/90: 2.0, GA/90: 2.0 → E[λ]: 2.474) | 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	Levante	Sevilla
League position	17.00	5.00
Points per game	1.11	1.64
Attack index	0.96	0.93
Defense (concede) index	0.90	1.11
Form multiplier	0.97	1.03
Standing λ multiplier	0.94	1.02

Lambda decomposition (how the goal rates were built)

Stage	Levante λ	Sevilla λ
FBref Squad Prior E[λ] (weight 0.228)	2.469	2.474
Pre-competitive-floor	1.472	1.569
Pre-calibration (Micro-duels)	1.527	1.515
Final λ	1.472	1.569

Scoreline distribution & markets

Top 5 scorelines	P
1-2	8.7%
1-1	11.1%
2-1	8.1%
0-1	7.4%
1-0	7.0%

Home win	35.8%
Draw	24.2%
Away win	40.0%
Over 2.5	58.6%
BTTS yes	61.1%

Pregame fair line — favorite Sevilla (40.0%), fair total 3.04, fair spread -0.10

Projected players vs season baseline

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

Levante — 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
Thiago Fernández	F	71	0	0.12	0.04	176%	1	0.8	6.8	51.4	30	FBref Prior F_service
Iván Romero	F	73	1	0.40	0.25	59%	2	1.7	6.9	59.2	29	FBref Prior F_service
Roger Brugué	F	82	0	0.35	0.34	ok	2	1.8	6.8	47.2	19	XGBoost F_service
Jon Ander Olasagasti	M	84	0	0.12	0.09	ok	1	0.9	6.9	61.9	30	XGBoost M_service
Oriol Rey	M	86	0	0.04	0.01	451%	0	0.2	6.8	33.6	28	FBref Prior M_service
Enzo Bardeli	M	79	0	0.05	0.01	411%	1	0.2	6.7	44.6	9	FBref Prior M_service
Manuel Sánchez	D	88	0	0.01	0.01	ok	0	0.2	6.7	53.0	30	XGBoost D_service
Aïssa Mandi	D	85	0	0.01	0.01	ok	0	0.1	6.8	46.1	9	FBref Prior D_service
Adrián de la Fuente	D	87	0	0.15	0.12	ok	1	1.3	7.0	64.3	29	FBref Prior D_service
Jeremy Toljan	D	84	0	0.03	0.01	193%	0	0.2	6.6	59.0	30	FBref Prior D_service
Mathew Ryan	G	90	0	0.00	0.01	100%		0.1	7.0	65.7	31	FBref Prior G_service
Team totals			1	1.47			10			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Pablo Cunat Campos	G	4.4m	10.9%	Market-value substitute prior
Axel Tape	D	13.8m	31.1%	Market-value substitute prior
Matias Moreno	D	13.7m	30.5%	Market-value substitute prior
Carlos Álvarez	M	22.6m	31.9%	Market-value substitute prior
Hugo Sotelo	M	22.1m	50.3%	Market-value substitute prior
Etta Eyong	F	25.9m	58.5%	Market-value substitute prior

Sevilla — 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
Youssouf Fofana	M	83	0	0.20	0.05	310%	1	0.7	6.8	40.3	7	XGBoost M_service
Miguel Sierra	F	75	1	0.20	0.04	382%	1	0.8	6.8	40.2	26	XGBoost F_service
Lucien Agoumé	M	88	0	0.07	0.02	271%	1	0.5	6.9	61.5	30	FBref Prior M_service
Giorgi Kochorashvili	M	74	0	0.09	0.01	604%	1	0.4	6.9	37.2	9	FBref Prior M_service
Gabriel Suazo	D	87	0	0.01	0.01	ok	0	0.1	6.7	54.7	28	FBref Prior D_service
Kike Salas	D	90	0	0.09	0.06	60%	1	0.8	6.8	62.3	28	FBref Prior D_service
Andrés Castrin	D	89	0	0.05	0.01	247%	1	0.3	6.9	44.0	27	XGBoost D_service
Juan Iglesias	D	90	0	0.08	0.03	152%	1	0.6	6.8	63.0	31	XGBoost D_service
Odysseas Vlachodimos	G	90	0	0.00	-	n/a		0.0	7.1	60.3	31	FBref Prior G_service
Félix Correia	F	76	0	0.19	0.03	492%	1	0.3	6.8	33.8	12	XGBoost F_service
Robbie Ure	F	80	1	0.27	0.04	566%	2	0.6	6.7	37.9	10	FBref Prior F_service
Team totals			2	1.57			13			6.8

Bench Candidates (7 modeled substitutes with empirical playing time)

Player	Pos	Exp Min	App Prob	Substitute Modeling Details
Fran González	G	4.4m	10.9%	Market-value substitute prior
José Ángel Carmona	D	14.0m	31.6%	Market-value substitute prior
Arouna Sangante	D	13.8m	22.2%	Market-value substitute prior
Oso	M	22.3m	51.5%	Market-value substitute prior
Djibril Sow	M	22.2m	50.8%	Market-value substitute prior
Lucas Stassin	F	25.9m	58.6%	Market-value substitute prior

Antagonist / tactical summary

Away midfield dictates play with ~52% possession expected (Enzo Bardeli vs Youssouf Fofana). Total antagonist xG — Home: 0.91, Away: 0.62. Home danger zone: Right Wing vs Left Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Midfield — possession 47.6% / 52.4%, dominance ratio 0.44, key duel: Enzo Bardeli vs Youssouf Fofana

Thiago Fernández xG 0.10Iván Romero xG 0.34Roger Brugué xG 0.30Giorgi Kochorashvili xG 0.06Robbie Ure xG 0.17Miguel Sierra xG 0.12

Summary

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

Tactical parity between 4-3-3 and 4-2-3-1. Match outcome driven primarily by individual player quality. Away midfield dictates play with ~52% possession expected (Enzo Bardeli vs Youssouf Fofana). Total antagonist xG — Home: 0.91, Away: 0.62. Home danger zone: Right Wing vs Left Back — Flank Battle. Away danger zone: Striker vs Two Centre Backs — 1v2 Aerial/Physical Battle.

Generated 2026-10-12 13:38:56 UTC · Soccer prediction reporting