| Score | Likelihood | Prob | Fair odds | |
|---|---|---|---|---|
| 1–1MODE | 8.9% | 11.18 | ||
| 2–1 | 8.4% | 11.84 | ||
| 1–2 | 7.6% | 13.20 | ||
| 2–2 | 7.2% | 13.99 | ||
| 3–1 | 5.3% | 18.82 | ||
| 1–0 | 5.3% | 18.92 | ||
| 2–0 | 5.0% | 20.05 | ||
| 0–1 | 4.7% | 21.09 |
FC Groningen scores shown first. Bivariate Poisson with team xG from recent form — most-likely score ≠ most-likely winner.
Probabilities derived from a Poisson model on expected goals. Edge % shown only when the book posts both sides of a market.
| Combo | Joint prob | Naïve (book) | Corr. | Fair odds |
|---|---|---|---|---|
Home win + BTTS home + btts | 27.2% | 29.7% | -8% | 3.67 |
Home win + Over 2.5 home + total_goals_2.5 | 32.6% | 29.7% | +10% | 3.07 |
Away win + BTTS away + btts | 22.7% | 24.3% | -7% | 4.40 |
Away win + Over 2.5 away + total_goals_2.5 | 26.4% | 24.4% | +8% | 3.79 |
Joint probability comes from the score grid (the truth). Naïve is what a book gets by multiplying legs — they undershoot correlated positive legs like "home + BTTS" and overshoot anti-correlated ones like "draw + over 2.5". Buy positive correlation; avoid negative.
Model probabilities FC Groningen 45.3% · Draw 25.7% · NEC 29.0% Why FC Groningen is favoured NEC's Elo (1500) is +10 over FC Groningen (1490); low confidence. Recent: FC Groningen 3W-2D-5L · NEC 3W-6D-1L (last 10). Goal differential per game: FC Groningen +0.1, NEC +0.5. Form depth FC Groningen: avg 1.6 goals scored, 1.5 conceded per game (2/5 at home, 1/5 on the road). NEC: avg 1.7 goals scored, 1.2 conceded per game (1/5 at home, 2/5 on the road). FC Groningen on a 2-match losing streak. NEC on a 3-draw streak. Goals expectation Model expects ~3.0 total goals (FC Groningen 1.4, NEC 1.6) — above the 2.5-goal mid line. But — counter-arguments Elo confidence is low (5%) — ratings are based on a thin sample, so the prediction itself is wider than the headline number suggests. Head-to-head 2 prior meetings — FC Groningen 0W, 2D, NEC 0W (draws are common). Last 3: 2-0, 2-1, 6-0. Confidence note Elo data on these teams is thin (5% sample-size confidence); this is a low-conviction match overall — bet only with strong reason from outside the model.