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
TOT
50.0%2.00−8.9 pp
Draw
29.9%3.34+7.2 pp
CRY
20.1%4.98+1.7 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
Spurs50.4%1.99
Draw29.7%3.37
Crystal Palace19.9%5.02
Double chance
Spurs or draw80.1%1.25
Spurs or Crystal Palace70.3%1.42
Draw or Crystal Palace49.6%2.02
Draw no bet
Spurs71.7%1.40
Crystal Palace28.3%3.53
A draw returns the stake, so these prices exclude it.
Win to nil
Spurs33.1%3.02
Crystal Palace12.3%8.10
Clean sheet
Spurs45.8%2.18
Crystal Palace25.0%3.99
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.
Unavailable players18% home against 32% away xG missing
Favours TOT. 10 out and 6 doubtful for TOT, 7 out and 5 doubtful for CRY; measured as the share of recent expected goals those players contributed
Underlying expected goals+0.83 net xG per match
Favours TOT. TOT +0.13, CRY -0.69 across the form window — results are noisier than the chances behind them
Recent form1.60 against 0.80 points per game
Favours TOT. last 5 and 5 completed matches: WWDLD against LLWDL
Home advantage+60 Elo equivalent
Favours TOT. 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
Team rating gap-17 Elo
Favours CRY. TOT 1477 against CRY 1494, 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
Ch 04 · Comparison
Both sides
TOT
WWDLD
12 Sept – 24 Oct
CRY
LDWLL
12 Sept – 25 Oct
1.60Points per game0.80
8Goals for5
5Goals against11
6.45Expected goals6.97
1,477Elo1,494
Head to head over 10 meetings in the seasons held (Premier League from 2021-22, Championship from 2024-25): TOT 6, drawn 0, CRY 4. 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
6.00
Betfred
16.7%
49
h2h
draw
4.70
Betfair Exchange
21.3%
49
h2h
home
1.71
1xBet
58.5%
49
Ch 06 · Availability
Spurs
17.8% xG out
Share of attacking output is what moves the number, so it is shown rather than implied.
Pedro PorroDEFinjured0%4.8% xG
Hamstring injury - Expected back 24 Oct
SávioMIDinjured0%4.6% xG
Muscular injury - Expected back 21 Nov
BergvallMIDinjured0%1.0% xG
Knee injury - Expected back 31 Oct
BentancurMIDsuspended0%0.2% xG
Suspended until 7 Nov
MudrykMIDinjured0%
Ankle injury - Unknown return date
RicharlisonFWDunavailable0%
not included in squad.
TosinDEFinjured0%
Calf injury - Unknown return date
UdogieDEFinjured0%
Knee injury - Unknown return date
OdobertMIDinjured0%
Knee injury - Unknown return date
XaviMIDinjured0%
Knee injury - Unknown return date
and 6 more
Ch 06 · Availability
Crystal Palace
31.5% xG out
Share of attacking output is what moves the number, so it is shown rather than implied.
MatetaFWDsuspended0%17.2% xG
Suspended until 2 Dec
DisasiDEFsuspended0%2.8% xG
Suspended until 25 Oct
ChilwellDEFinjured0%2.4% xG
Unspecified injury - Unknown return date
Chadi RiadDEFinjured0%
Knee injury - Unknown return date
SarrMIDinjured0%
Groin injury - Expected back 8 Nov
TomiyasuDEFinjured0%
Calf injury - Expected back 8 Nov
UcheFWDunavailable0%
has returned to Getafe CF
Strand LarsenFWDdoubtful75%12.4% xG
Ankle injury - 75% chance of playing
KhalailiDEFdoubtful75%10.9% xG
Hamstring injury - 75% chance of playing
NketiahFWDdoubtful75%9.9% xG
Unspecified injury - 75% chance of playing
and 2 more
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 assigns Spurs a 50.6% win chance, with 29.7% for the draw and 19.7% for Crystal Palace. Expected goals are 1.41 for Spurs and 0.78 for Palace. Over 2.5 goals is rated at 37.2%, while both teams scoring is 41.5%.
Spurs have taken 1.6 points per game across 5 matches, compared with Palace’s 0.8. Spurs’ recent xG figures are 6.4 for and 5.8 against; Palace’s are 7.0 for and 10.4 against. The 10-match head-to-head record is 6 Spurs wins and 4 Palace wins, with no draws.
The market is more favourable to Spurs than the model: 60.1% versus 50.6%, and less favourable to the draw: 21.9% versus 29.7%. The scorecard does not show the model beating the closing market. There are 16 unmeasured Spurs absentees and 12 for Palace, so their attacking-output impact is not known.
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 awaymodel 20.1% vs 6.00 (Best available)+20.6 ppstake 1.0%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