Prediction review
Sunday, 30 August 2026
On 2026-08-30 we had published a prediction for 56 fixtures before kick-off. We called 30 of them correctly, 54%.
Our strongest call, and it missed
The most confident thing we published was Feyenoord Rotterdam to beat ADO Den Haag, at 87.1%. It finished 2–2. That is the day's boldest call and its largest error in one fixture. A model that is never surprised is not saying much; the question is whether it is surprised this often at this level, and that only answers itself over months rather than over one evening.
When we were confident
16 of the day's calls were at 60% or above. 10 of them landed. Over a single day that number means very little — it is the same figure across a month that says whether our stated confidence is honest.
The ones we called close
15 fixtures were split closely enough that no outcome reached 40%. 3 of them ended level. We publish these without pretending to a view: a fixture the model divides three ways is one it has little to tell you about, and saying so is more useful than manufacturing a lean.
Coverage
The day's predictions spanned 17 competitions: Eredivisie (5), Brasileirao (5), Premier League (4).
Only predictions published before the match day are counted. Results come from public fixture feeds. How the model is measured →