About Fulltime Stats
Fulltime Stats publishes statistical football predictions in plain English. For each match we show a win / draw / win probability split, the most-likely scoreline, and a "fair odds" figure — all produced by our own model from expected-goals data. The site carries no bookmaker odds and no gambling-affiliate content.
How predictions are generated
Predictions come from our own Poisson / Dixon-Coles model — not from any third-party or bookmaker prediction. The pipeline works like this:
- For every team we estimate an attack and defence rating from its recent expected goals (xG) for and against — falling back to actual goals where xG isn't available.
- Those ratings are adjusted for the quality of the opponents faced (strength of schedule): a goal against a strong defence counts for more than one against a weak side. Newly-promoted teams and teams with little data are handled with a cautious prior.
- Ratings are regularised toward the league average so a small, one-sided sample can't produce an over-confident prediction.
- The two teams' ratings become each side's expected goals for the fixture, then a Poisson score matrix (with a Dixon-Coles low-score correction) turns that into the 1/X/2 split, the most-likely scoreline, and derived markets like both-teams-to-score and over/under 2.5.
Head-to-head history and match statistics are shown on the match page for context, but the current model is driven by the expected-goals ratings above. Player-level factors such as injuries and suspensions are not yet part of the model — a planned improvement.
Tracking our accuracy
Every prediction is logged before kick-off and later checked against the actual result. The homepage shows a running, automatically-updated record of how often the model's 1/X/2 call and exact scoreline were right — good and bad. We think a predictions site should show its track record openly.
Fair odds explained
Alongside each probability we show a "fair odds" figure. This is simply the mathematical conversion of our model's probability into decimal-odds format: fair odds = 100 ÷ probability. For example, a 42% chance converts to fair odds of 2.38. It represents the break-even price for that outcome according to our model. These figures come entirely from our own statistical model — they are not odds offered by, quoted from, or linked to any betting operator, and this site carries no bookmaker advertising.
What our predictions are — and are not
Advertising on this site
Fulltime Stats is supported by standard display advertising, kept clearly separate from the predictions and analysis. We have no commercial relationship with any team, competition, or gambling operator.
Data sources
Fixtures, results, live scores, standings, expected-goals and player data come from API-Football (api-sports.io). The data is refreshed automatically several times a day; live scores reflect the most recent refresh. The prediction model, ratings and all editorial framing are our own.