AI Predictions

Poisson match modelling and expected points, computed on the server

ID 1900182 –

Prediction engine active • computed on the server

Gameweek 3 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 3 Next

Match Outcomes

10 Fixtures

Friday 4 September

Ipswich Town
20:00
Liverpool
20% 23% draw 56%
1.14 xG Liverpool favourites 2.00 xG

Saturday 5 September

Newcastle
12:30
Bournemouth
41% 26% draw 33%
1.60 xG Newcastle favourites 1.41 xG
Brentford
15:00
Sunderland
48% 27% draw 25%
1.64 xG Brentford favourites 1.12 xG
Brighton
15:00
Leeds
45% 27% draw 28%
1.60 xG Brighton favourites 1.22 xG
Fulham
15:00
Crystal Palace
39% 28% draw 33%
1.40 xG Fulham favourites 1.26 xG
Man City
15:00
Coventry City
75% 17% draw 8%
2.49 xG Man City strong favourites 0.75 xG
Nott'm Forest
15:00
Spurs
45% 27% draw 28%
1.59 xG Nott'm Forest favourites 1.23 xG
Hull City
17:30
Aston Villa
26% 27% draw 48%
1.17 xG Aston Villa favourites 1.67 xG

Sunday 6 September

Everton
14:00
Man Utd
34% 27% draw 39%
1.36 xG Man Utd favourites 1.48 xG
Arsenal
16:30
Chelsea
56% 25% draw 19%
1.78 xG Arsenal favourites 0.95 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.