National League · Tuesday, 15 September 2026. Final score 1–0 (half-time 1–0). Rebuilt from the season as it stood that morning, our rating would have been 62% for over 2.5 goals. This match is older than our frozen ratings ledger, which keeps 30 days, so that figure is a reconstruction from pre-match data rather than a number we published at the time — a distinction worth making, because only the frozen ones prove what we actually said beforehand.
Open this match in the app →| Market | Yes | No | Our call |
|---|---|---|---|
| Over 2.5 goals | 62% | 38% | Over |
| Over 3.5 goals | 38% | 62% | no pick |
| Both teams to score | 61% | 39% | no pick |
The result model puts Worthing at 45%, the draw at 24% and AFC Hornchurch at 32%, from expected goals of 1.8 and 1.49.
The league sets the starting point. National League has produced over 2.5 goals in 58% of its matches, and that is where a team with no record of its own would sit.
Each side's own record. Worthing have 6 in 7 this season (3 of 4 at home), AFC Hornchurch 5 in 7 (4 of 4 away). Those records are pulled toward the league rate with the weight of about 24 matches — enough that two or three unusual games cannot swing a rating — giving 64% and 61%.
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 61%.
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 64%, from expected goals of 1.8 for Worthing and 1.49 for AFC Hornchurch. Folding in 30% of that view gives 62%.
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.
| Team | Games | O2.5 | O3.5 | BTTS |
|---|---|---|---|---|
| Worthing | 7 | 86% | 71% | 86% |
| AFC Hornchurch | 7 | 71% | 29% | 43% |
More: Worthing season stats · AFC Hornchurch season stats · National League table and form. Ratings are calibrated probabilities, not tips — a 60% call is expected to miss two times in five.