AI Predictions

Poisson match modelling and expected points, computed on the server

ID 1900182 –

Prediction engine active • computed on the server

Gameweek 8 Predictions

A Poisson goal model forecasts every fixture; the xPts engine scores every player from their per-90 rates, expected minutes and fixture difficulty.

Prev Gameweek 8 Next

Match Outcomes

10 Fixtures

Friday 23 October

Ipswich Town
20:00
Nott'm Forest
30% 27% draw 43%
1.27 xG Nott'm Forest favourites 1.55 xG

Saturday 24 October

Aston Villa
12:30
Man City
26% 26% draw 48%
1.20 xG Man City favourites 1.69 xG
Arsenal
15:00
Everton
64% 23% draw 13%
1.93 xG Arsenal strong favourites 0.77 xG
Coventry City
15:00
Fulham
31% 28% draw 42%
1.25 xG Fulham favourites 1.50 xG
Chelsea
17:30
Spurs
57% 24% draw 20%
1.97 xG Chelsea favourites 1.10 xG

Sunday 25 October

Crystal Palace
14:00
Newcastle
35% 27% draw 38%
1.38 xG Too close to call 1.45 xG
Hull City
14:00
Brentford
28% 27% draw 45%
1.24 xG Brentford favourites 1.60 xG
Liverpool
14:00
Brighton
51% 25% draw 24%
1.85 xG Liverpool favourites 1.21 xG
Man Utd
14:00
Bournemouth
55% 24% draw 21%
1.94 xG Man Utd favourites 1.16 xG
Sunderland
16:30
Leeds
42% 29% draw 30%
1.43 xG Sunderland favourites 1.17 xG

Player Projections

Top 20

How these numbers are produced

Match outcomes

Attack and defence ratings are fitted for every club from three seasons of real matches — expected goals, shots on target and the closing betting market — weighted towards recent form and pulled back towards the league average where the evidence is thin. Those set an expected goal rate for both sides, and summing a Poisson grid over every scoreline gives the home / draw / away probabilities, with a correction for how much more often real football ends 0-0 and 1-1 than independence predicts. A club with no top-flight record yet falls back to FPL's own strength ratings.

Player expected points

Per-90 rates for goals, assists, saves, bonus and cards are scored against the real FPL points rules — a clean sheet is the opponent's own goal rate failing to produce a goal, and the conceded deduction is the expected value of the rule rather than half the expected goals. Early in a season those rates are shrunk towards the player's previous season, so one quiet opener does not become his level. That structural estimate is blended with a form prior and with FPL's own next-gameweek estimate, weighted by how much of a record there is to read.