Weekly review
Week of 14 September
14 September 2026 – 20 September 2026 · 1,261 words
Between 14 September and 20 September we had published a prediction before kick-off for 242 fixtures, across 7 days and 25 competitions. We called 112 of them correctly, 46.3%.
Does our confidence mean anything
Taking every call in the period and sorting it by how confident we were: we said under 40% on 39 fixtures, averaging 38.2%, and were right 33.3% of the time; we said 40 to 50% on 94 fixtures, averaging 44.9%, and were right 31.9% of the time; we said 50 to 60% on 54 fixtures, averaging 54.3%, and were right 51.9% of the time; we said 60 to 70% on 36 fixtures, averaging 64.0%, and were right 75.0% of the time. The band that misses is 40 to 50%: we overstated it by 13.0 points across 94 fixtures. That is the number to hold us to, and it is the one we would most like to see shrink. At the other end, 50 to 60% came out within 2.4 points of what we claimed, on 54 fixtures — there, the figure on the card means what it says.
The outcome we almost never call
Of 242 fixtures, 59 ended level — 24.4% of them. We called a draw in none of them. Not rarely: never, and that is worth explaining rather than apologising for. The three probabilities on each card come from simulating the two sides' scoring rates independently and counting how often each outcome appears. That method has a built-in ceiling on the draw: across this period the highest draw probability we published was 31.4%, and the nearest a draw ever came to leading its fixture was 5.0 points short. For the draw to top a card, two teams would have to be so exactly matched that neither win is likelier than the tie — which is rarer than a tie itself. So the headline call cannot name the outcome that happens a quarter of the time, and roughly a quarter of our misses are lost before kick-off. Independence is also the part we would change first. Real football scores are not independent at the low end: 0-0 and 1-1 happen more often than two separate rates predict, which is why the standard correction in the literature exists and why our draw numbers are likely a little low across the board. Until that is fixed, the probability we print for the draw is the figure worth reading on a tight fixture — not the call above it.
Home, away, and which we get right
We backed the home side 170 times and the visiting side 72, so 70% of our calls went to the home team. They landed 47.6% of the time. The away calls landed 43.1%. Here the home calls are the sounder ones, which is the more ordinary result: home advantage is real and the model is reading it rather than assuming it.
The goals we expected
Underneath the win probabilities sit two expected-goals figures, and they are the part of the model that is easiest to check and hardest to fudge. Across 242 fixtures we expected 1.50 goals for the home side and 1.20 for the away side, a total of 2.71. What actually happened was 1.62 and 1.21, a total of 2.83. The home figure is the one that drifts: we were under by 0.12 of a goal per match. It is small in absolute terms and it is systematic, which is the more interesting property — a bias that holds across hundreds of fixtures is correctable in a way that a wide spread is not. Rounding each expectation to a whole number reproduced the exact scoreline 33 times, 13.6%. We mention that as a curiosity rather than a claim: nobody should be predicting exact scorelines, and a model that appeared good at it would be a model that had been overfitted.
The high-scoring flag, tested
One model on each card does nothing but estimate how likely the home side is to score four goals or more. Over 242 fixtures that happened 19 times, 7.9%. The flag was raised on 174 of them, 72% of what we published. That is too often to mean anything: a warning attached to most fixtures is a decoration rather than a warning, and we would rather say so than leave it decorating the cards. Where it was raised, the home side reached four goals 10.9% of the time; where it was not, 0.0%. So it is separating the two, by a factor of about 109.2. That is what the flag is asked to do, and worth stating plainly given it is also the part of the output we have most recently had to correct.
The calls we backed hardest
19 calls were published at 70% or above. 14 of them came in, 73.7%, against an average stated confidence of 76.1%. The most expensive of them was Aris to beat Iraklis at 85.2%, which finished 0–0 — a draw, which is the outcome we structurally cannot call.
The call we would point to
The call we are most pleased with is not the most confident one, it is the one furthest from the price. Aston Villa to beat Coventry City in EFL Cup: we published 62.6% where the odds implied about 45.5%, a gap of 17.1 points, and it finished 1–3. 5 calls in this period were that far above the market and came in. We list one rather than all of them because a page of the ones that worked, with the ones that did not left out, is how a track record gets quietly turned into advertising — the figure for how that whole group did is in the section above, and it is not flattering.
Where we were most wrong
Aris against Iraklis, in Greek Super League, finished 0–0. We had published Aris to beat Iraklis at 85.2%, the largest confidence we placed on anything that did not happen in this period. It stays on the record. A site that reports only its hits is not reporting a record, it is reporting a selection.
Against last week
Against the week before: 227 settled fixtures then at 47.1%, 242 now at 46.3%, a move of -0.9 points. More useful than the headline: in the 50 to 70% range, where most of our calls sit, we were 7.3 points below our stated confidence last week and 2.9 points above it this one. That gap narrowing is the only kind of improvement we would claim. The headline difference itself is small enough that we would not call it a change at all.
Where we published
We published across 25 competitions. The five busiest were La Liga (20), UEFA Europa League (17), Championship (14), Segunda Division (12), League One (12). None of them has reached 20 settled fixtures in this period, which is the least we would want before ranking one competition against another.
How to read all this
One week of 242 fixtures settles very little on its own. A percentage point either way on a sample this size is noise, and we would rather say so than dress it up. What these reviews are for is the shape that emerges when several of them sit side by side: whether a stated 65% keeps landing near 65%, whether the gap between our number and the market's keeps costing us, whether a competition we read badly this week is still being read badly in three. Those are answerable, and they are answerable in public, which is the only reason to publish the bad figures alongside the good ones.
Every figure here comes from predictions published before the match day — never from a re-run after the results were known. Results come from public fixture feeds. Every period we have reviewed → How the model is measured →