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
NEW
49.8%2.01+5.6 pp
Draw
24.4%4.10−0.9 pp
BOU
25.8%3.88−4.7 pp
Ch 02 · Book
27 markets
dixon_coles xi001-20260903
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
Newcastle49.8%2.01
Draw24.4%4.10
Bournemouth25.8%3.88
Double chance
Newcastle or draw74.2%1.35
Newcastle or Bournemouth75.6%1.32
Draw or Bournemouth50.2%1.99
Draw no bet
Newcastle65.9%1.52
Bournemouth34.1%2.93
A draw returns the stake, so these prices exclude it.
Win to nil
Newcastle23.5%4.26
Bournemouth11.1%8.98
Clean sheet
Newcastle28.9%3.46
Bournemouth16.5%6.05
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.
Home advantage+60 Elo equivalent
Favours NEW. 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 form1.60 against 1.20 points per game
Favours NEW. last 5 and 5 completed matches: WDLWD against DLDDW
Team rating gap-31 Elo
Favours BOU. NEW 1555 against BOU 1586, 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 players3% home against 0% away xG missing
Favours BOU. 4 out and 0 doubtful for NEW, 4 out and 0 doubtful for BOU; measured as the share of recent expected goals those players contributed
Underlying expected goals-0.02 net xG per match
Favours BOU. NEW -0.35, BOU -0.34 across the form window — results are noisier than the chances behind them
Ch 04 · Comparison
Both sides
NEW
WDLWD
10 May – 29 Aug
BOU
WDDLD
9 May – 29 Aug
1.60Points per game1.20
8Goals for5
6Goals against5
6.63Expected goals7.02
1,555Elo1,586
Head to head over 8 meetings in the seasons held (Premier League from 2021-22, Championship from 2024-25): NEW 0, drawn 5, BOU 3. 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
3.25
Smarkets
30.8%
43
h2h
draw
3.90
1xBet
25.6%
43
h2h
home
2.27
GTbets
44.1%
43
Ch 06 · Availability
Newcastle
2.6% xG out
Share of attacking output is what moves the number, so it is shown rather than implied.
OsulaFWDinjured0%2.6% xG
Foot injury - Unknown return date
BurnDEFinjured0%
Ankle injury - Expected back 14 Sep
JoelintonMIDinjured0%
Unspecified injury - Unknown return date
LivramentoDEFinjured0%
Calf injury - Unknown return date
Ch 06 · Availability
Bournemouth
0.0% xG out
Share of attacking output is what moves the number, so it is shown rather than implied.
AdliMIDinjured0%
Unspecified injury - Unknown return date
J.AraujoDEFinjured0%
Thigh injury - Unknown return date
Kroupi.JrMIDinjured0%
Foot injury - Unknown return date
MilosavljevićDEFinjured0%
Unspecified injury - Unknown return date
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 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 homemodel 49.8% vs 2.27 (GTbets)+13.1 ppstake 2.0%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