Football ratings

Wednesday 14 October 2026 · times UK

The model's strongest calls

Nothing clears the bar today. The thresholds are set where the model has historically been as good as it claims — home win 70%, away win 60% — and a quiet day is a real answer, not a gap.

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.

71%Manchester City v Paris Saint Germain — over 2.5 goals20:00 · market 66% · this strong, 76% land (485 cases)

62%Norwich v Southampton — over 2.5 goals19:45 · market 64% · this strong, 66% land (4,584 cases)

62%Feyenoord v Como — over 2.5 goals17:45 · market 64% · this strong, 66% land (4,584 cases)

Every fixture

Championship

Norwich v Southampton19:45

	Home	Draw	Away
Model	36	25	39
Market	39	25	36

	Over 2.5	Under 2.5
Model	62	38
Market	64	36

Under 4.5 goals: 75% · happens 86% of the time anyway

Portsmouth v Sheffield Utd19:45

	Home	Draw	Away
Model	50	26	23
Market	40	28	31

	Over 2.5	Under 2.5
Model	53	47
Market	48	52

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.

QPR v Derby19:45

	Home	Draw	Away
Model	52	27	21
Market	58	24	18

	Over 2.5	Under 2.5
Model	50	50
Market	52	48

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

Lincoln v West Ham20:00

	Home	Draw	Away
Model	22	26	52
Market	21	24	55

	Over 2.5	Under 2.5
Model	51	49
Market	54	46

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

UEFA Champions League

New competition — experimental. The model has never been trained or tested on it, these clubs are rated across leagues whose ratings have never been calibrated against each other, and the probabilities use a fallback calibration. Treat them as much weaker than the domestic ones.

Feyenoord v Como17:45

	Home	Draw	Away
Model	60	23	18
Market	27	24	49

	Over 2.5	Under 2.5
Model	62	38
Market	64	36

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

Model is 32 points above the market on home win (pinnacle). Worth a look at why.

Lask Linz v Liverpool17:45

Not rated — Lask Linz has 0 prior matches in the store, most likely promoted from a division we do not collect. A rating built on that would be a guess wearing a percentage.

AS Roma v Real Madrid20:00

	Home	Draw	Away
Model	42	26	32
Market	26	24	50

	Over 2.5	Under 2.5
Model	58	42
Market	66	34

Under 4.5 goals: 81% · happens 86% of the time anyway

Model is 16 points above the market on home win (pinnacle). Worth a look at why.

Aston Villa v Fenerbahçe20:00

	Home	Draw	Away
Model	27	26	47
Market	56	23	21

	Over 2.5	Under 2.5
Model	59	41
Market	61	39

Under 4.5 goals: 81% · happens 86% of the time anyway

Model is 27 points above the market on away win (pinnacle). Worth a look at why.

Bodo/Glimt v Borussia Dortmund20:00

Not rated — Bodo/Glimt has 0 prior matches in the store, most likely promoted from a division we do not collect. A rating built on that would be a guess wearing a percentage.

Manchester City v Paris Saint Germain20:00

	Home	Draw	Away
Model	69	18	12
Market	47	24	29

	Over 2.5	Under 2.5
Model	71	29
Market	66	34

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

Model is 23 points above the market on home win (pinnacle). Worth a look at why.

Real Betis v FC Porto20:00

	Home	Draw	Away
Model	23	25	53
Market	46	26	27

	Over 2.5	Under 2.5
Model	59	41
Market	55	45

Under 4.5 goals: 81% · happens 86% of the time anyway

Model is 25 points above the market on away win (pinnacle). Worth a look at why.

Shakhtar Donetsk v AEK Athens FC20:00

Not rated — AEK Athens FC has 0 prior matches in the store, most likely promoted from a division we do not collect. A rating built on that would be a guess wearing a percentage.

Slovan Bratislava v VfB Stuttgart20:00

Not rated — Slovan Bratislava has 0 prior matches in the store, most likely promoted from a division we do not collect. A rating built on that would be a guess wearing a percentage.

How the calls did

✕RB Leipzig 1–0 PSV Eindhoven over 2.5 goals 76%

✕Atletico Madrid 2–0 Manchester United over 2.5 goals 64%

✕RB Leipzig 1–0 PSV EindhovenPSV Eindhoven away win 61%

✓Galatasaray 1–4 Barcelona over 2.5 goals 61%

1 of 4 settled since yesterday · 275 of 418 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 7/14, we claimed 50% · 415/847 all-time

what actually happenedwe gave it 39% on average

·Over/under 2.5top pick right 8/14, we claimed 57% · 484/847 all-time

what actually happenedwe gave it 49% 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%.

9 rated · 4 not rated · model goals_v7_cal · built 2026-10-14 12:23 UK