Our model · SharpCast

The SharpEngine pipeline: point in time data feeds a Dixon Coles and Elo forecast engine, which builds one scoreline matrix; markets are derived, ensembled with the de overrounded bookmaker consensus, calibrated, AI reviewed, then selected, settled and monitored. Dixon Coles and Elo remain the sole source of every published number. — The SharpEngine pipeline. Every published number is built this way, and the Dixon Coles and Elo engine remains the sole source of each one.

1What we model

At the core sits a Dixon Coles goals model, extended with time decay, an expected goals blend and Bayesian shrinkage, then blended with the de overrounded bookmaker consensus. The whole engine reduces to two lines. The first builds one calibrated probability matrix over every scoreline:

P_SC(x, y) = Normalize( DC(x, y)^1−λ · M(x, y)^λ · C(x, y) )

Dixon Coles sets the shape, the market keeps it honest, context tilts it. The second line reads every market off that single matrix:

P(market) = Σ P_SC(x, y) over all (x, y) ∈ market

There is no separate model per market, which is why a SharpCast Builder uses the true joint probabilities rather than the bookmaker style assumption that the legs are independent. Term definitions live in the glossary.

2How picks are chosen

For every fixture the model produces a probability and an edge for every market in scope. We rank by probability first, with value as the tiebreak, because the bankroll is built by picking winners.

Conviction Score

A 0 to 100 display number that ranks picks the same way the selector does. It is a display summary only. It does not pick the bet; the selector does.

3How the record is kept honest

Every SharpCast Pick is committed before kickoff and stamped with the time it was filed, shown on each fixture. The full record is kept on this site. Nothing is quietly removed: settled outcomes stand, every miss stays visible, and the strike rate is computed from every settled pick, wins and losses alike. Live settled metrics are on the record, and Closing Line Value against the closing price is our gold standard measure of model quality.

AI verification

The numbers come first. The model output is the record; the words only explain it.