How it works

The model estimates probabilities from the statistics of played matches. It is not a prediction of the result and not a promise of winnings — it is a way to see which outcome looks most likely, and why.

Data

Three recent seasons across 47 competitions: results, corners, cards, shots, possession, referees. Statistics refresh every four hours, injury data every two, bookmaker odds twice a day.

Goals

At the core is the Dixon-Coles model: each team gets an attacking and a defensive rating, with home advantage estimated separately. A match loses weight as it ages, so recent form counts for more than last year. A low-score correction fixes the well-known weakness of simple models, which overstate draws.

Every goal market is derived from the same score distribution. That is why the result, the totals and both-teams-to-score always agree with each other.

Corners and cards

These work similarly but follow a different distribution: their spread is wider than Poisson, and a simple model understates the extreme totals. Cards have a third factor — the referee. It is measured as the ratio of actual cards to those expected from the matches he worked, not as a plain average: a strict referee assigned to quiet games would otherwise look lenient.

The referee layer is switched on only where the data supports it. In some leagues the referee is known for fewer than three quarters of matches — there the layer is off.

What else counts

Rest days and fixture congestion are counted across all competitions at once, European ties included: a Wednesday in the Champions League is the main source of fatigue. An upcoming European tie counts too, when a team may hold players back.

Calibration

Once a week the model is checked against past matches: if it said 60%, such events should happen roughly 60% of the time. Probabilities are corrected from those checks. The average shift across leagues stays within three percentage points.

What we do not do

We do not claim to beat bookmakers. The main markets at large firms are priced very sharply, and an honest backtest confirms it. The value here is different: a full breakdown across every market in one place, with the factors you would otherwise collect by hand across several sites.

We also do not display invented success rates. If a public results counter ever appears, it will be built on immutable prediction records — written to the database at publication and never rewritten afterwards.