AGFVSBragaAtalantaVSKairat AlmatyFC MidtjyllandVSAjax AmsterdamFC ThunVSHearts

Serie A prediction accuracy

Every forecast is locked before kickoff (normally 24 hours before), hashed into our public ledger and graded on the 90-minute result. Misses stay on the record. Published forecasts and the backtest are reported separately and never mixed.

Data batch updated Early sample: 7 graded
RPS0.242Not enough rounds for an interval
Log loss0.947Lower is better
Picks graded71 Nov – 2 Nov 2026
Correct (1X2)85.7%Most likely result came true
Brier score0.546Sum over H/D/A, 0–2
Coverage100.0%0 awaiting grading · 0 excluded

Model comparison

ModelnCorrectRPSBrierLog loss
Final (published)V1: equals the statistical model785.7%0.24150.54610.9466
Statistical modelElo + Dixon-Coles785.7%0.24150.54610.9466
ClaudeAI analyst · shadow0––––
CodexAI analyst · shadow0––––
Base rateBenchmark: league H/D/A frequency757.1%0.26050.58360.9723
Elo onlyBenchmark771.4%0.25650.57831.0011

The n column shows how many matches each row covers, so only compare scores between rows with the same n. Lowest RPS among the rows with the most matches is in bold. Claude and Codex have only run on some matches so far and stay in shadow: they are graded but not used in the published probability (V1). The AI layer section compares them with the statistical model on the same matches.

Calibration

Graded published forecasts in five bins by the top probability, with 95% intervals.

30%30%40%40%50%50%60%60%70%70%80%80%90%90%< 45%: predicted 39%, observed 100% (n = 4)55–65%: predicted 63%, observed 50% (n = 2)65–75%: predicted 74%, observed 100% (n = 1)Predicted probability of the pick

Our picksPerfect calibration

Top probabilitynPredictedObserved95% CI
< 45%439%100%51–100%
45–55%0–––
55–65%263%50%9–91%
65–75%174%100%21–100%
≥ 75%0–––

By confidence tier

TiernCorrectBacktest
High1100.0%70–83%
Medium250.0%about 61%
Low4100.0%39–49%

High: top probability 65% or more · Medium: 50–65% · Low: under 50%. Totals include Low picks.

By market

"Simple rule" is the benchmark in the note under each market.

MarketCorrectSimple rule
Result (1X2)Always pick the home team85.7%57.1%
Correct score: most likely overallExact scores land about one time in eight0.0%–
Correct score: most likely in the pick0.0%–
Over/Under 2.5 goalsAlways pick the more common side28.6%57.1%
Both teams to scoreClose to the base rate: little skill shown so far57.1%57.1%

AI layer – shadow, not yet used in published probabilities

No graded match has the AI layer yet. Claude and Codex forecast each match in shadow from the day before kickoff; their record appears here once those matches are graded. The AI layer gets a weight only after at least 300 graded matches and the other conditions on the methodology page.

Methodology

Grading rules

Graded on the 90-minute score; extra time and penalties are ignored. Every forecast locked before kickoff counts. We lock 24 hours before kickoff, or straight away when a match enters our tracking later than that; each match page shows the actual lock time. Forecasts locked after kickoff are never graded. Corrections are logged, never silently replaced.

Grading methodology

Exclusion log

No exclusions so far.

Forecast archive

Every graded forecast with its locked probabilities, result and hash. Download the full ledger as CSV or JSON.

Browse graded resultsOpen the ledger

Other leagues: Premier LeagueLa LigaBundesligaLigue 1Primeira LigaScottish PremiershipEredivisieSüper LigEFL ChampionshipSaudi Pro LeagueChampions LeagueEuropa LeagueConference League All leagues

For information and entertainment only. Not betting advice. 18+. Predictions are probabilities, not certainties. Responsible gambling