Football ratings

Friday 18 September 2026 · times UK

The model's strongest calls

86%Bayern München — home winBayern München v Union Berlin · 19:30 · market 91% · this strong, 87% land (475 cases)

£10 on all 1 as one multiple returns about £11 if every one lands. The model puts that at 86%, the market at 91%, and the price needs 94% 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.

80%Bayern München v Union Berlin — over 2.5 goals19:30 · market 85% · this strong, 75% land (134 cases)

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

56%Espanyol v Elche — under 2.5 goals20:00 · market 48% · this strong, 58% land (10,295 cases)

Every fixture

Premier League

Brentford v Chelsea20:00

	Home	Draw	Away
Model	44	27	29
Market	35	25	40

	Over 2.5	Under 2.5
Model	57	43
Market	65	35

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

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

Championship

Bristol City v Watford20:00

	Home	Draw	Away
Model	49	27	24
Market	51	26	23

	Over 2.5	Under 2.5
Model	50	50
Market	51	49

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

La Liga

Espanyol v Elche20:00

	Home	Draw	Away
Model	46	29	25
Market	52	27	20

	Over 2.5	Under 2.5
Model	44	56
Market	52	48

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

Model is 6 points below the market on home win (pinnacle). Worth a look at why.

Serie A

Monza v Sassuolo19:45

	Home	Draw	Away
Model	34	29	38
Market	33	28	39

	Over 2.5	Under 2.5
Model	48	52
Market	53	47

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

Bundesliga

Bayern München v Union Berlin19:30

	Home	Draw	Away
Model	86	10	4
Market	91	5	3

	Over 2.5	Under 2.5
Model	80	20
Market	85	15

Under 4.5 goals: 58% · happens 86% of the time anyway

Ligue 1

Monaco v Lens19:45

	Home	Draw	Away
Model	45	25	30
Market	46	26	28

	Over 2.5	Under 2.5
Model	62	38
Market	62	38

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

La Liga 2

Albacete v Cordoba19:30

	Home	Draw	Away
Model	39	28	32
Market	40	26	34

	Over 2.5	Under 2.5
Model	50	50
Market	57	43

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

Eredivisie

Groningen v PEC Zwolle19:00

	Home	Draw	Away
Model	55	25	20
Market	58	24	19

	Over 2.5	Under 2.5
Model	58	42
Market	66	34

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

Super Lig

Kasımpaşa v Konyaspor18:00

	Home	Draw	Away
Model	48	29	24
Market	39	28	32

	Over 2.5	Under 2.5
Model	46	54
Market	48	52

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

Model is 8 points above the market on home win (pinnacle). Worth a look at why.

How the calls did

No calls have been settled since yesterday.

0 of 0 settled since yesterday · 202 of 300 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 2/3, we claimed 48% · 283/576 all-time

what actually happenedwe gave it 45% on average

·Over/under 2.5top pick right 1/3, we claimed 54% · 337/576 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 · 0 not rated · model goals_v7_cal · built 2026-09-18 07:06 UK