Football ratings

Wednesday 28 October 2026 · times UK

The model's strongest calls

78%Celtic — home winCeltic v Dundee Utd · 19:45 · market 76% · this strong, 82% land (2,727 cases)

74%Inter — away winVenezia v Inter · 17:30 · market 71% · this strong, 74% land (779 cases)

65%Napoli — away winMonza v Napoli · 19:45 · market 55% · this strong, 71% land (1,529 cases)

£10 on all 3 as one multiple returns about £30 if every one lands. The model puts that at 38%, the market at 30%, and the price needs 34% 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.

69%Celtic v Dundee Utd — over 2.5 goals19:45 · market 71% · this strong, 70% land (1,528 cases)

67%Venezia v Inter — over 2.5 goals17:30 · market 71% · this strong, 70% land (1,528 cases)

62%Monza v Napoli — over 2.5 goals19:45 · market 58% · this strong, 66% land (4,584 cases)

62%Heart Of Midlothian v Rangers — over 2.5 goals20:00 · market 61% · this strong, 66% land (4,584 cases)

Every fixture

Serie A

AC Milan v Bologna17:30

	Home	Draw	Away
Model	66	22	12
Market	56	24	19

	Over 2.5	Under 2.5
Model	52	48
Market	53	47

Under 4.5 goals: 84% · happens 86% of the time anyway

Model is 10 points above the market on home win (pinnacle). Worth a look at why.

Parma v Udinese17:30

	Home	Draw	Away
Model	28	28	44
Market	34	31	35

	Over 2.5	Under 2.5
Model	49	51
Market	43	57

Under 4.5 goals: 87% · happens 86% of the time anyway

Model is 9 points above the market on away win (pinnacle). Worth a look at why.

Venezia v Inter17:30

	Home	Draw	Away
Model	10	16	74
Market	12	17	71

	Over 2.5	Under 2.5
Model	67	33
Market	71	29

Under 4.5 goals: 67% · happens 86% of the time anyway

Genoa v Juventus19:45

	Home	Draw	Away
Model	17	25	58
Market	18	25	57

	Over 2.5	Under 2.5
Model	48	52
Market	45	55

Under 4.5 goals: 87% · happens 86% of the time anyway

Monza v Napoli19:45

	Home	Draw	Away
Model	15	20	65
Market	22	23	55

	Over 2.5	Under 2.5
Model	62	38
Market	58	42

Under 4.5 goals: 73% · happens 86% of the time anyway

Model is 11 points above the market on away win (pinnacle). Worth a look at why.

Scottish Premiership

Aberdeen v Falkirk19:45

	Home	Draw	Away
Model	48	26	26
Market	45	27	28

	Over 2.5	Under 2.5
Model	58	42
Market	52	48

Under 4.5 goals: 82% · happens 86% of the time anyway

Celtic v Dundee Utd19:45

	Home	Draw	Away
Model	78	15	7
Market	76	16	8

	Over 2.5	Under 2.5
Model	69	31
Market	71	29

Under 4.5 goals: 69% · happens 86% of the time anyway

Dundee v Kilmarnock19:45

	Home	Draw	Away
Model	50	27	23
Market	49	25	26

	Over 2.5	Under 2.5
Model	52	48
Market	61	39

Under 4.5 goals: 86% · happens 86% of the time anyway

ST Johnstone v Motherwell19:45

	Home	Draw	Away
Model	25	27	47
Market	38	28	34

	Over 2.5	Under 2.5
Model	52	48
Market	53	47

Under 4.5 goals: 87% · happens 86% of the time anyway

Model is 13 points above the market on away win (pinnacle). Worth a look at why.

ST Mirren v Hibernian19:45

	Home	Draw	Away
Model	26	26	48
Market	31	26	43

	Over 2.5	Under 2.5
Model	56	44
Market	58	42

Under 4.5 goals: 83% · happens 86% of the time anyway

Heart Of Midlothian v Rangers20:00

	Home	Draw	Away
Model	34	25	40
Market	29	26	46

	Over 2.5	Under 2.5
Model	62	38
Market	61	39

Under 4.5 goals: 78% · happens 86% of the time anyway

How the calls did

✓AS Roma 4–2 CagliariAS Roma home win 70%

✕Sheffield Wednesday 1–1 Cambridge United over 2.5 goals 62%

1 of 2 settled since yesterday · 355 of 529 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 7/8, we claimed 55% · 562/1111 all-time

what actually happenedwe gave it 52% on average

·Over/under 2.5top pick right 7/8, we claimed 57% · 640/1111 all-time

what actually happenedwe gave it 54% 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%.

11 rated · 0 not rated · model goals_v7_cal · built 2026-10-28 06:03 UK