NB I · Friday, 21 August 2026 · 16:30. Our rating makes this 67% to go over 2.5 goals, so our lean is over. The NB I average is 60%.
Open this match in the app →| Market | Yes | No | Our call |
|---|---|---|---|
| Over 2.5 goals | 67% | 33% | Over |
| Over 3.5 goals | 41% | 59% | no pick |
| Both teams to score | 64% | 36% | Yes |
The result model puts Paks at 45%, the draw at 21% and Ujpest at 34%, from expected goals of 2.1 and 1.8.
| Market | Price | Implied | Our rating | Edge |
|---|---|---|---|---|
| Over 2.5 goals | 1.50 | 63% | 67% | +5% |
| Under 2.5 goals | 2.50 | 38% | 33% | -5% |
| Both teams to score | 1.57 | 59% | 64% | +5% |
Implied percentages have the bookmaker's margin removed, so they add to 100 and can be compared with our rating directly. Edge is simply the gap between the two. A positive edge means our model thinks the outcome is likelier than the price suggests — it is not a tip, and a high probability with a negative edge is a poor bet however safe it looks. Prices are a pre-match snapshot from a single bookmaker and move constantly.
Match odds: Paks 1.60, draw 4.00, Ujpest 4.20.
The league sets the starting point. NB I has produced over 2.5 goals in 60% of its matches, and that is where a team with no record of its own would sit.
Each side's own record. Paks have 4 in 4 this season (2 of 2 at home), Ujpest 3 in 4 (2 of 2 away). 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 66% and 64%.
Last season still counts, briefly. With 4 and 4 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 62% and 66%.
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 63%.
Head to head. These sides have met 8 times in three years, producing over 2.5 goals in 75%. That nudges the number 10% of the way toward the head-to-head pattern — deliberately small, because fixtures change more than reputations do — landing on 64%.
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 75%, from expected goals of 2.1 for Paks and 1.8 for Ujpest. Folding in 30% of that view gives 67%.
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: Paks season stats · Ujpest season stats · NB I table and form. Ratings are calibrated probabilities, not tips — a 60% call is expected to miss two times in five.