The bar is the model's probability; the caret on the same scale is the market's, with the margin removed. The distance between them is the disagreement.
OutcomeModel fill · market caretProbFairΔ mkt
AVL
41.2%2.43−6.6 pp
Draw
31.8%3.15+5.3 pp
FUL
27.1%3.70+1.3 pp
Ch 02 · Book
27 markets
dixon_coles xi001-20261102
Model fair prices, computed as 1 / probability from a Dixon-Coles score matrix. No bookmaker margin is included, and no bookmaker is quoting these. A real price will be shorter than every number here.
Match result
Aston Villa46.3%2.16
Draw30.1%3.33
Fulham23.6%4.23
Double chance
Aston Villa or draw76.4%1.31
Aston Villa or Fulham69.9%1.43
Draw or Fulham53.7%1.86
Draw no bet
Aston Villa66.2%1.51
Fulham33.8%2.96
A draw returns the stake, so these prices exclude it.
Win to nil
Aston Villa29.4%3.40
Fulham14.3%7.00
Clean sheet
Aston Villa41.5%2.41
Fulham26.3%3.80
Ch 03 · Reasoning
What is driving this
computed, not generated
Computed arithmetic, not generated text. Each driver is a stored quantity: the Elo difference replayed from results, points per game over the last five matches, rolling expected goals, and each absent player's share of team expected goals.
Underlying expected goals-0.64 net xG per match
Favours FUL. AVL -0.33, FUL +0.31 across the form window — results are noisier than the chances behind them
Team rating gap+94 Elo
Favours AVL. AVL 1611 against FUL 1517, computed from stored results; an Elo-driven model scores RPS around 0.2015 on this league against roughly 0.194 for de-vigged closing odds
Unavailable players10% home against 4% away xG missing
Favours FUL. 4 out and 10 doubtful for AVL, 2 out and 6 doubtful for FUL; measured as the share of recent expected goals those players contributed
Home advantage+60 Elo equivalent
Favours AVL. the football default is around 100 Elo points, but Premier League home advantage fell during the crowdless 2020/21 season and settled lower afterwards, so the ratings carry a smaller term
Recent form2.00 against 1.60 points per game
Favours AVL. last 5 and 5 completed matches: WWDWL against WWLDD
Ch 04 · Comparison
Both sides
AVL
WWDWL
12 Sept – 24 Oct
FUL
DDLWW
12 Sept – 24 Oct
2.00Points per game1.60
9Goals for4
7Goals against3
7.36Expected goals7.26
1,611Elo1,517
Head to head over 8 meetings in the seasons held (Premier League from 2021-22, Championship from 2024-25): AVL 6, drawn 0, FUL 2. Cup ties and earlier seasons are not included, so a full-history site will show more.
Ch 05 · Market
Bookmaker prices
Real bookmaker prices, collected from published market data.
Market
Selection
Best
Book
Implied
N
h2h
away
5.70
Betfair
17.5%
49
h2h
draw
4.20
Betfair
23.8%
49
h2h
home
2.16
1xBet
46.3%
49
Ch 06 · Availability
Aston Villa
9.6% xG out
Share of attacking output is what moves the number, so it is shown rather than implied.
CashDEFsuspended0%1.9% xG
Suspended until 21 Nov
RuggeriDEFinjured0%0.3% xG
Hamstring injury - Expected back 2 Jan
Wan-BissakaDEFinjured0%
Hamstring injury - Expected back 21 Nov
OnanaMIDinjured0%
Knee injury - Unknown return date
ManzambiMIDdoubtful75%14.7% xG
Calf injury - 75% chance of playing
BarkleyMIDdoubtful75%4.8% xG
Unspecified injury - 75% chance of playing
MaatsenDEFdoubtful75%3.7% xG
Ankle injury - 75% chance of playing
PauDEFdoubtful75%2.4% xG
Hamstring injury - 75% chance of playing
AlyssonMIDdoubtful75%1.8% xG
Unspecified injury - 75% chance of playing
GoretzkaMIDdoubtful75%1.7% xG
Knee injury - 75% chance of playing
and 4 more
Ch 06 · Availability
Fulham
3.6% xG out
Share of attacking output is what moves the number, so it is shown rather than implied.
SessegnonDEFsuspended0%1.9% xG
Suspended until 7 Nov
TeteDEFinjured0%
Concussion - Expected back 10 Oct
RobinsonDEFdoubtful75%2.9% xG
Ankle injury - 75% chance of playing
AffengruberDEFdoubtful75%1.9% xG
Unspecified injury - 75% chance of playing
LarssonMIDdoubtful75%1.4% xG
Groin injury - 75% chance of playing
Smith RoweMIDdoubtful75%0.4% xG
Knock - 75% chance of playing
CairneyMIDdoubtful75%0.2% xG
Knee injury - 75% chance of playing
De FougerollesDEFdoubtful75%
Unspecified injury - 75% chance of playing
Ch 07 · Simulation
Re-price without a player
Removing a player scales that side's expected goals by their share of recent attacking output, then rebuilds the score matrix. Every market moves together.
Ch 08 · Briefing
Written summary
generated text
Written by gpt-5.6-terra from the numbers above, which it cannot add to or override.
The model makes Aston Villa the most likely winner at 42.5%, with the draw at 31.3% and Fulham at 26.2%. It projects 1.23 expected goals for Villa and 0.91 for Fulham. The 36.2% probability of over 2.5 goals and 43.2% probability of both teams scoring point to a relatively low-scoring profile.
Villa have 3 wins, 1 draw and 1 loss in 5, scoring 9 goals from 7.4 xG while allowing 9.0 xG. Fulham’s 5-game record is 2 wins, 2 draws and 1 loss, with 4 goals from 7.3 xG and 5.7 xG conceded. Villa have won 6 of the 8 head-to-head meetings, although Fulham won the latest one 1-0.
The market is more positive on Villa, assigning them 49.3% versus the model’s 42.5%, and lower on the draw at 25.8% versus 31.3%. The scorecard says the model does not beat the closing market. There are no named missing players, but Villa have 14 further unmeasured absentees and Fulham have 8.
Ch 09 · Divergence
Where the model differs from a price
Shown with the model's own record, because that is what decides how much these are worth.
h2h drawmodel 31.8% vs 3.85 (Betfair Exchange)+22.2 ppstake 2.0%medium confidence
h2h awaymodel 27.1% vs 4.10 (Betfair Exchange)+10.9 ppstake 0.9%medium confidence
Ch 10 · Calibration
How this model actually scores
Dixon-Coles bivariate Poisson fitted to Premier League results with exponential time decay. Statistical model, no language model involved.
loses to closing market2,281 out-of-sample fixtures
Metric
Model
Market
Δ
Ranked probability score
0.2047
0.1965
+0.0082
Log loss
0.9882
0.9623
+0.0259
Brier
0.5883
0.5711
+0.0172
Accuracy
52.5%
54.8%
−2.3 pp
Lower is better for the first three. These probabilities are for reading a fixture, not for expecting profit against closing prices. What these numbers mean