Research & methodology
Football is a distribution, not a prediction.
Metis is a probabilistic football modelling project. Rather than producing a single score prediction or a binary pick, Metis models the full range of ways a match can unfold. For every fixture, the system estimates each team's scoring environment and builds a coherent scoreline distribution, from which match outcomes, expected goals, totals, clean-sheet probabilities and fantasy projections can all be derived.
That same distribution sits underneath the match pages and the Fantasy engine across Metis. The objective is not to make football look more certain than it is. It is to make the uncertainty useful.
The model
One match model, many derived questions
At the centre of Metis is an independently developed generative match model. The current system estimates home and away scoring intensity using regression and chronologically updated measures of team strength and match context. A fixture must be forecast using only information available before that fixture — no hindsight, no retro-fitting.
From the estimated scoring parameters, Metis generates a joint scoreline distribution. This means the probabilities shown across the site are internally connected rather than independently generated headline predictions: the win probability, the over/under split, the both-teams-to-score figure and the clean-sheet chance on a match page all come from the same underlying distribution.
The market
A benchmark, not an enemy
Betting markets are exceptionally strong football forecasters, and Metis says so plainly. Two forecasts appear on Metis, and they are kept deliberately distinct:
- Raw MetisThe independent statistical forecast, produced before any market information is applied. Stored separately, so the model can be evaluated honestly against the market.
- Metis ForecastThe public forecast. Where fresh de-vigged market prices are available, the headline 1X2 probabilities are anchored to them while retaining the scoreline structure required for everything downstream — a market-anchored Metis distribution. Where no fresh price exists, or the last price is too old to use, the independent model is published unchanged. Every match page states which of the two it is showing, per fixture.
The point of the anchoring is coherence: a public forecast that benefits from the market's information, expressed as a full distribution the market does not publish.
Players
From matches to players
Player projections are built on top of the match distributions. For Fantasy Premier League, the engine combines the match-level scoring environment with player-level estimates: start probability, expected minutes, goal and assist involvement, clean-sheet contribution and expected points.
Because the engine works with distributions rather than point estimates, it can also report a floor, median and ceiling for a player's score, and the probability of a blank or a haul. Two players with identical expected points can have very different risk profiles — that difference is often the real decision.
Scenarios
Conditioning on match states
A generative model can be asked conditional questions: how does the forecast move if a particular team scores first, or if a key player does not start? The engine supports that class of question, but no scenario tool is currently served on the site — it is planned, not published. Nothing on Metis today lets you re-run a fixture under a different assumption, and the published forecast is always the unconditional one.
Evaluation
How forecasts are judged
Single-match accuracy is a misleading measure of a probabilistic forecaster: a good model is often "wrong" in any one match and right in the long run. Metis is evaluated the way probability forecasts should be:
- Calibration — when the model says 60%, it should happen about 60% of the time.
- Ranked Probability Score — a proper scoring rule over the ordered home/draw/away outcome.
- Market comparison — the raw model scored against the de-vigged Pinnacle opening price on the same matches, which is the benchmark of record. Closing prices are used separately, to measure how a forecast moves relative to the market between the open and kickoff; they are not the yardstick the model is scored against.
- Walk-forward evaluation — out-of-sample only; a fixture is always forecast with data available before kickoff.
Accountability
A forecast you can check
Every published forecast is stored with its timestamp, model version and market-anchor status, and results are settled against it. The long-term aim is visible performance — including the bad periods. A forecast that cannot be checked is not particularly useful.
Scope
What Metis is — and isn't
Metis is
Football modelling. Probability. Research. Decision support.
Metis is not
Guaranteed profit. Locks. Certainty. Tipster picks.
Matches — match distributions. Fantasy — player-level decisions. Markets — future quantitative market research and backtesting.
The World Cup 2026 model that started this project is preserved as a tracked public archive, including its full forecast-vs-reality retrospective.
Football, in probabilities.