Coppa Italia · Monday, 17 August 2026 · 17:00. Our rating makes this 40% to go over 2.5 goals, though we make no pick on this fixture — see below. The Coppa Italia average is 47%.
Open this match in the app →| Market | Yes | No | Our call |
|---|---|---|---|
| Over 2.5 goals | 40% | 60% | no pick |
| Over 3.5 goals | 18% | 82% | no pick |
| Both teams to score | 46% | 54% | no pick |
The result model puts Pisa at 20%, the draw at 29% and Empoli at 51%, from expected goals of 0.71 and 1.31.
The league sets the starting point. Coppa Italia has produced over 2.5 goals in 47% of its matches, and that is where a team with no record of its own would sit.
Each side's own record. Pisa have 20 in 38 this season (7 of 19 at home), Empoli 0 in 0. Those records are pulled toward the league rate with the weight of about 32 matches — enough that two or three unusual games cannot swing a rating — giving 47% and 47%.
Last season still counts, briefly. With 38 and 0 games played this season, last season's rates are still blended in and fade out entirely by game 14 — the point at which our testing showed they stop adding accuracy. That moves the two figures to 47% and 47%.
The mix. Weighted 40% home side, 40% away side and 20% league — the split that beat every alternative across 30,582 matches of testing — that gives 47%.
Goal expectation. Separately a Poisson model built from attack and defence strength — using real expected-goals data where the league has it — puts this match at 33%, from expected goals of 0.71 for Pisa and 1.31 for Empoli. Folding in 30% of that view gives 43%.
Season opener. One of these sides has not played a league game yet. Openers run about 2.5 points under their league's norm, measured across 2,727 of them, so the rating is docked to 40%.
This breakdown is generated from the same inputs the rating uses, so it cannot describe a calculation we did not perform. The full model is set out in the methodology.
More: Pisa season stats · Empoli season stats · Coppa Italia table and form. Ratings are calibrated probabilities, not tips — a 60% call is expected to miss two times in five.