Football ratings

Friday 9 October 2026 · times UK

The model's strongest calls

79%PSV Eindhoven — home winPSV Eindhoven v Heerenveen · 19:00 · market 77% · this strong, 82% land (2,727 cases)

75%Galatasaray — home winGalatasaray v Kasımpaşa · 18:00 · market 76% · this strong, 82% land (2,727 cases)

70%Borussia Dortmund — home winBorussia Dortmund v Werder Bremen · 19:30 · market 73% · this strong, 78% land (4,355 cases)

£10 on all 3 as one multiple returns about £20 if every one lands. The model puts that at 41%, the market at 43%, and the price needs 49% 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.

74%PSV Eindhoven v Heerenveen — over 2.5 goals19:00 · market 84% · this strong, 76% land (485 cases)

64%Galatasaray v Kasımpaşa — over 2.5 goals18:00 · market 66% · this strong, 66% land (4,584 cases)

63%West Ham v QPR — over 2.5 goals20:00 · market 62% · this strong, 66% land (4,584 cases)

63%Moreirense v GIL Vicente — under 2.5 goals18:45 · market 57% · this strong, 61% land (2,190 cases)

56%SC Braga v Sporting CP — under 2.5 goals20:15 · market 47% · this strong, 58% land (10,295 cases)

Every fixture

Championship

West Ham v QPR20:00

	Home	Draw	Away
Model	67	20	13
Market	64	20	16

	Over 2.5	Under 2.5
Model	63	37
Market	62	38

Under 4.5 goals: 74% · happens 86% of the time anyway

La Liga

Malaga v Espanyol20:00

	Home	Draw	Away
Model	30	29	40
Market	34	31	35

	Over 2.5	Under 2.5
Model	45	55
Market	45	55

Under 4.5 goals: 89% · happens 86% of the time anyway

Bundesliga

Borussia Dortmund v Werder Bremen19:30

	Home	Draw	Away
Model	70	20	10
Market	73	16	11

	Over 2.5	Under 2.5
Model	59	41
Market	69	31

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

Ligue 1

Lens v Lyon19:45

	Home	Draw	Away
Model	41	27	33
Market	41	26	33

	Over 2.5	Under 2.5
Model	57	43
Market	63	37

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

Eredivisie

PSV Eindhoven v Heerenveen19:00

	Home	Draw	Away
Model	79	14	7
Market	77	12	10

	Over 2.5	Under 2.5
Model	74	26
Market	84	16

Under 4.5 goals: 63% · happens 86% of the time anyway

Primeira Liga

Moreirense v GIL Vicente18:45

	Home	Draw	Away
Model	27	31	42
Market	28	30	41

	Over 2.5	Under 2.5
Model	37	63
Market	43	57

Under 4.5 goals: 93% · happens 86% of the time anyway

SC Braga v Sporting CP20:15

	Home	Draw	Away
Model	25	29	46
Market	29	27	45

	Over 2.5	Under 2.5
Model	44	56
Market	53	47

Under 4.5 goals: 90% · happens 86% of the time anyway

Super Lig

Galatasaray v Kasımpaşa18:00

	Home	Draw	Away
Model	75	17	8
Market	76	15	9

	Over 2.5	Under 2.5
Model	64	36
Market	66	34

Under 4.5 goals: 77% · happens 86% of the time anyway

How the calls did

No calls have been settled since yesterday.

0 of 0 settled since yesterday · 233 of 353 since the model went live.

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 2026-10-09 07:08 UK