Football ratings

Tuesday 27 October 2026 · times UK

The model's strongest calls

70%AS Roma — home winAS Roma v Cagliari · 19:45 · market 72% · this strong, 78% land (4,355 cases)
£10 on all 1 as one multiple returns about £13 if every one lands. The model puts that at 70%, the market at 72%, and the price needs 75% just to break even.Bookmaker margin compounds with every leg, which is why the break-even sits above the market's own view. A same-match bet builder pays less than this — the bookmaker prices in that the legs move together. Our chance is a straight multiplication and is if anything a little low: where two legs of one match both cleared, they landed together 55.5% of the time against a multiplied 53.4%.

Goals — supporting, not headline

These are calibrated — a 65% call lands about 65% of the time. But the model separates high- from low-scoring matches far less sharply than it separates winners, so there is less information behind a goals number than a result one.

62%Sheffield Wednesday v Cambridge United — over 2.5 goals19:45 · market 57% · this strong, 66% land (4,584 cases)

Every fixture

League One
Leicester v Wigan19:45
HomeDrawAway
Model602417
Market681913
Over 2.5Under 2.5
Model5842
Market6535
Under 4.5 goals: 83%  ·  happens 86% of the time anyway
Model is 8 points below the market on home win (pinnacle). Worth a look at why.
Luton v Doncaster19:45
HomeDrawAway
Model582418
Market622118
Over 2.5Under 2.5
Model5743
Market6337
Under 4.5 goals: 83%  ·  happens 86% of the time anyway
Milton Keynes Dons v Bromley19:45
HomeDrawAway
Model582418
Market592219
Over 2.5Under 2.5
Model5743
Market5941
Under 4.5 goals: 83%  ·  happens 86% of the time anyway
Oxford United v Stockport County19:45
HomeDrawAway
Model373033
Market282547
Over 2.5Under 2.5
Model4753
Market5545
Under 4.5 goals: 90%  ·  happens 86% of the time anyway
Model is 9 points above the market on home win (pinnacle). Worth a look at why.
Sheffield Wednesday v Cambridge United19:45
HomeDrawAway
Model462528
Market472528
Over 2.5Under 2.5
Model6238
Market5743
Under 4.5 goals: 79%  ·  happens 86% of the time anyway
Serie A
Sassuolo v Lazio17:30
HomeDrawAway
Model232552
Market292645
Over 2.5Under 2.5
Model5644
Market5842
Under 4.5 goals: 80%  ·  happens 86% of the time anyway
Model is 8 points above the market on away win (pinnacle). Worth a look at why.
AS Roma v Cagliari19:45
HomeDrawAway
Model701911
Market72199
Over 2.5Under 2.5
Model5842
Market5941
Under 4.5 goals: 78%  ·  happens 86% of the time anyway
Torino v Como19:45
HomeDrawAway
Model212455
Market182557
Over 2.5Under 2.5
Model5743
Market5842
Under 4.5 goals: 79%  ·  happens 86% of the time anyway

How the calls did

✓Galatasaray 2–1 Fenerbahçe over 2.5 goals 67%
✕Paris Saint Germain 2–0 Lyon over 2.5 goals 62%
✓Santa Clara 1–2 BenficaBenfica away win 62%
✓Sevilla 2–0 Osasuna under 2.5 goals 58%

3 of 4 settled since yesterday · 354 of 527 since the model went live.

Every match, for the record

The model rates the whole card, not just the calls, and learns from all of it. Judged as probabilities rather than picks — a 38% favourite losing is the model working, not failing.

·Resulttop pick right 6/7, we claimed 52% · 555/1103 all-time
what actually happenedwe gave it 51% on average
·Over/under 2.5top pick right 5/7, we claimed 57% · 634/1103 all-time
what actually happenedwe gave it 52% on average

A well-calibrated model's average claim matches how often it happens. That is the number Rule 9 gates on, and it is tracked for results and goals alike whether or not a fixture ever produced a call.

What these numbers are. The model's own estimate of how likely each result is, from form, Elo, rest, shots and xG as they stood at 06:00 UK on match day. One bivariate Poisson produces all of them, so the result and the goals figures share one underlying view of the match. Each published figure is then calibrated against what actually happened in past matches, one market at a time — so they agree closely but are not forced to agree exactly. Market figures are the bookmaker's prices with their margin removed, so the two are comparable.

What they are not. Across 57,633 out-of-sample fixtures the market separated matches better than the model in every league, every season, every outcome and every confidence band — 24 slices, no exceptions, re-tested in August 2026 on the current model. This is a second opinion, not an edge. Where it earns its keep is honesty about its own confidence: when it says 74%, that happens about 74% of the time.

Why a call appears. Thresholds — home 70% · away 60% · over 60% · under 55% — sit where the model has historically been as good as its claim. Raising them would surface fewer calls and be less accurate about them, because its confidence above those levels is inflated everywhere except home wins. Draws are never flagged: the highest one ever rated was 62%.

8 rated · 0 not rated · model goals_v7_cal · built 2026-10-27 06:02 UK