| Score | Likelihood | Prob | Fair odds | |
|---|---|---|---|---|
| 0–1MODE | 19.3% | 5.19 | ||
| 0–0 | 18.8% | 5.33 | ||
| 1–1 | 12.5% | 8.03 | ||
| 1–0 | 12.1% | 8.25 | ||
| 0–2 | 9.9% | 10.10 | ||
| 1–2 | 6.4% | 15.63 | ||
| 2–1 | 4.0% | 24.85 | ||
| 2–0 | 3.9% | 25.54 |
Australia 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 | 5.6% | 6.9% | -19% | 17.84 |
Home win + Over 2.5 home + total_goals_2.5 | 6.6% | 5.3% | +24% | 15.14 |
Away win + BTTS away + btts | 10.3% | 13.4% | -23% | 9.73 |
Away win + Over 2.5 away + total_goals_2.5 | 14.8% | 10.4% | +42% | 6.78 |
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 Australia 45.5% · Draw 25.6% · Egypt 29.0% Why Australia is favoured Egypt's Elo (1515) is +15 over Australia (1500); low confidence. Recent: Australia 1W-1D-1L · Egypt 1W-2D-0L (last 3). Goal differential per game: Australia +0.0, Egypt +0.7. Form depth Australia: avg 0.7 goals scored, 0.7 conceded per game (1/1 at home, 0/2 on the road). Egypt: avg 1.7 goals scored, 1.0 conceded per game (0/1 at home, 1/2 on the road). Goals expectation Model expects ~2.0 total goals (Australia 0.8, Egypt 1.2) — below 2.5. But — counter-arguments Elo confidence is low (15%) — ratings are based on a thin sample, so the prediction itself is wider than the headline number suggests. Context Australia has 2 more days of rest (Australia 19d, Egypt 17d). Confidence note Elo data on these teams is thin (15% sample-size confidence); this is a low-conviction match overall — bet only with strong reason from outside the model.