Football ratings

Tuesday 15 September 2026 · times UK

The model's strongest calls

82%Ajax — home winAjax v Willem II · 19:00 · market 85% · this strong, 85% land (1,418 cases)

68%Real Madrid — away winElche v Real Madrid · 20:30 · market 78% · this strong, 71% land (1,529 cases)

65%Heart Of Midlothian — away winFalkirk v Heart Of Midlothian · 19:45 · market 51% · this strong, 68% land (2,602 cases)

£10 on all 3 as one multiple returns about £25 if every one lands. The model puts that at 36%, the market at 34%, and the price needs 41% 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.

73%Ajax v Willem II — over 2.5 goals19:00 · market 79% · this strong, 76% land (485 cases)

62%Falkirk v Heart Of Midlothian — over 2.5 goals19:45 · market 54% · this strong, 66% land (4,584 cases)

62%Elche v Real Madrid — over 2.5 goals20:30 · market 72% · this strong, 66% land (4,584 cases)

Every fixture

Championship

Bristol City v Lincoln19:45

	Home	Draw	Away
Model	44	28	28
Market	49	26	24

	Over 2.5	Under 2.5
Model	50	50
Market	51	49

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

Middlesbrough v Millwall19:45

	Home	Draw	Away
Model	45	26	28
Market	62	21	17

	Over 2.5	Under 2.5
Model	56	44
Market	59	41

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

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

La Liga

Rayo Vallecano v Espanyol18:00

	Home	Draw	Away
Model	43	28	30
Market	42	28	30

	Over 2.5	Under 2.5
Model	51	49
Market	50	50

Under 4.5 goals: 85% · happens 86% of the time anyway

Alaves v Valencia19:00

	Home	Draw	Away
Model	52	27	21
Market	52	29	19

	Over 2.5	Under 2.5
Model	49	51
Market	43	57

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

Elche v Real Madrid20:30

	Home	Draw	Away
Model	13	20	68
Market	9	13	78

	Over 2.5	Under 2.5
Model	62	38
Market	72	28

Under 4.5 goals: 76% · happens 86% of the time anyway

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

Scottish Premiership

Falkirk v Heart Of Midlothian19:45

	Home	Draw	Away
Model	14	21	65
Market	24	25	51

	Over 2.5	Under 2.5
Model	62	38
Market	54	46

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

Model is 14 points above the market on away win (pinnacle). Worth a look at why.

Hibernian v Kilmarnock19:45

	Home	Draw	Away
Model	55	25	21
Market	64	20	16

	Over 2.5	Under 2.5
Model	58	42
Market	63	37

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

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

Motherwell v Aberdeen19:45

	Home	Draw	Away
Model	67	21	12
Market	52	25	23

	Over 2.5	Under 2.5
Model	58	42
Market	56	44

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

Model is 15 points above the market on home win (pinnacle). Worth a look at why.

Eredivisie

Ajax v Willem II19:00

	Home	Draw	Away
Model	82	12	5
Market	85	9	6

	Over 2.5	Under 2.5
Model	73	27
Market	79	21

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

How the calls did

✓Inter 5–3 UdineseInter home win 78%

✓Como 2–1 ParmaComo home win 76%

✓Torino 0–2 AS RomaAS Roma away win 68%

✕Gaziantep FK 0–0 FenerbahçeFenerbahçe away win 66%

✕Gaziantep FK 0–0 Fenerbahçe over 2.5 goals 65%

✓Inter 5–3 Udinese over 2.5 goals 65%

✕Moreirense 3–1 Maritimo under 2.5 goals 57%

4 of 7 settled since yesterday · 194 of 291 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 6/9, we claimed 58% · 276/561 all-time

what actually happenedwe gave it 50% on average

·Over/under 2.5top pick right 5/9, we claimed 57% · 325/561 all-time

what actually happenedwe gave it 51% 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 · 0 not rated · model goals_v7_cal · built 2026-09-15 07:05 UK