| Score | Likelihood | Prob | Fair odds | |
|---|---|---|---|---|
| 0–1MODE | 22.9% | 4.36 | ||
| 0–2 | 19.0% | 5.27 | ||
| 0–0 | 13.8% | 7.22 | ||
| 0–3 | 10.5% | 9.55 | ||
| 1–1 | 7.4% | 13.50 | ||
| 1–2 | 6.1% | 16.31 | ||
| 1–0 | 4.5% | 22.35 | ||
| 0–4 | 4.3% | 23.07 |
Cusco FC 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 | 1.5% | 1.5% | -3% | 68.61 |
Home win + Over 2.5 home + total_goals_2.5 | 1.5% | 2.1% | -28% | 64.85 |
Away win + BTTS away + btts | 12.4% | 15.8% | -22% | 8.06 |
Away win + Over 2.5 away + total_goals_2.5 | 29.0% | 22.5% | +29% | 3.44 |
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 Cusco FC 41.6% · Draw 26.0% · Estudiantes de La Plata 32.4% Why Cusco FC is favoured Elo essentially level (1500 vs 1500) — winner depends on context. Recent: Cusco FC 0W-0D-3L · Estudiantes de La Plata 1W-2D-0L (last 3). Goal differential per game: Cusco FC -1.3, Estudiantes de La Plata +0.3. Form depth Cusco FC: avg 0.3 goals scored, 1.7 conceded per game (0/1 at home, 0/2 on the road). Estudiantes de La Plata: avg 1.3 goals scored, 1.0 conceded per game (1/2 at home, 0/1 on the road). Cusco FC on a 3-match losing streak. Goals expectation Model expects ~2.2 total goals (Cusco FC 0.7, Estudiantes de La Plata 1.5) — below 2.5. But — counter-arguments Elo confidence is low (30%) — ratings are based on a thin sample, so the prediction itself is wider than the headline number suggests. Confidence note Elo data on these teams is thin (30% sample-size confidence); this is a low-conviction match overall — bet only with strong reason from outside the model.