Premier League
This week’s forecasts.
Dixon-Coles bivariate Poisson. Probabilities only — the model is beaten by bookmaker closing odds and picks the correct result about 54% of the time. Not betting advice.
Price a fixture
Next fixtures
| Kick-off | Home | Away | H | D | A | xG | Score |
|---|---|---|---|---|---|---|---|
| Sat 10 Oct 11:30 |  Arsenal |
 Leeds |
65% | 24% | 12% | 1.9–0.7 | 2-0 |
| Sat 10 Oct 14:00 |  Aston Villa |
 Brentford |
40% | 27% | 33% | 1.6–1.4 | 1-1 |
| Sat 10 Oct 14:00 |  Chelsea |
 Bournemouth |
45% | 25% | 30% | 1.8–1.5 | 1-1 |
| Sat 10 Oct 14:00 |  Ipswich |
 Fulham |
31% | 28% | 40% | 1.3–1.5 | 1-1 |
| Sat 10 Oct 14:00 |  Sunderland |
 Brighton |
32% | 29% | 38% | 1.2–1.4 | 1-1 |
| Sat 10 Oct 16:30 |  Man United |
 Tottenham |
59% | 24% | 17% | 2.0–1.0 | 1-1 |
| Sun 11 Oct 13:00 |  Crystal Palace |
 Nott'm Forest |
37% | 29% | 34% | 1.4–1.3 | 1-1 |
| Sun 11 Oct 13:00 |  Hull |
 Everton |
31% | 34% | 35% | 1.0–1.1 | 1-1 |
| Sun 11 Oct 15:30 |  Liverpool |
 Man City |
31% | 27% | 42% | 1.4–1.6 | 1-1 |
| Mon 12 Oct 19:00 |  Coventry |
 Newcastle |
23% | 27% | 50% | 1.1–1.7 | 1-1 |
Hull v Everton: Hull has thin history (6.5 effective matches) — strength is shrunk toward baseline and this price is low-confidence
Coventry v Newcastle: Coventry has thin history (6.5 effective matches) — strength is shrunk toward baseline and this price is low-confidence
Fitted team strengths
| Team | Attack | Defence | Net |
|---|---|---|---|
| Arsenal | 1.434 | 0.597 | 2.403 |
| Man City | 1.541 | 0.725 | 2.125 |
| Liverpool | 1.382 | 1.030 | 1.342 |
| Brighton | 1.322 | 1.030 | 1.283 |
| Man United | 1.329 | 1.078 | 1.233 |
| Brentford | 1.221 | 1.057 | 1.155 |
| Bournemouth | 1.217 | 1.072 | 1.135 |
| Leeds | 1.117 | 0.990 | 1.129 |
| Chelsea | 1.324 | 1.176 | 1.126 |
| Nott'm Forest | 1.066 | 0.989 | 1.078 |
| Newcastle | 1.257 | 1.177 | 1.068 |
| Aston Villa | 1.110 | 1.089 | 1.019 |
| Everton | 0.976 | 0.969 | 1.007 |
| Fulham | 0.966 | 1.082 | 0.892 |
| Sunderland | 0.867 | 1.008 | 0.860 |
| Crystal Palace | 0.998 | 1.246 | 0.801 |
| Hull | 0.806 | 1.033 | 0.780 |
| Tottenham | 0.922 | 1.192 | 0.773 |
| Ipswich | 0.946 | 1.583 | 0.598 |
| Coventry | 0.677 | 1.392 | 0.486 |
Attack above 1 scores more than the division average; defence below 1 concedes less.
4748 matches, 2021-08-06 to 2026-09-14 ·
56 teams ·
home advantage 1.257 ·
decay half-life 198.0 days ·
xG model on, real (73% coverage)
Promoted this season: Coventry, Hull, Ipswich — shrunk toward a promoted-team
prior (attack 0.719, defence 1.309),
because promoted sides are markedly weaker than average and treating them as average is the
biggest source of early-season error.