AI Predictions

Poisson match modelling and expected points, computed on the server

ID 1900182 –

Prediction engine active • computed on the server

Gameweek 5 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 5 Next

Match Outcomes

10 Fixtures

Friday 18 September

Brentford
20:00
Chelsea
37% 27% draw 37%
1.47 xG Too close to call 1.47 xG

Saturday 19 September

Spurs
12:30
Aston Villa
38% 27% draw 35%
1.49 xG Too close to call 1.40 xG
Brighton
15:00
Arsenal
22% 27% draw 51%
1.03 xG Arsenal favourites 1.65 xG
Everton
15:00
Ipswich Town
56% 25% draw 20%
1.86 xG Everton favourites 1.03 xG
Newcastle
15:00
Hull City
56% 24% draw 20%
1.92 xG Newcastle favourites 1.06 xG
Nott'm Forest
17:30
Coventry City
57% 24% draw 18%
1.87 xG Nott'm Forest favourites 0.98 xG

Sunday 20 September

Leeds
14:00
Crystal Palace
37% 29% draw 34%
1.35 xG Too close to call 1.28 xG
Man City
14:00
Sunderland
66% 21% draw 13%
2.12 xG Man City strong favourites 0.83 xG
Bournemouth
14:00
Liverpool
34% 26% draw 39%
1.47 xG Too close to call 1.58 xG
Fulham
16:30
Man Utd
29% 27% draw 44%
1.27 xG Man Utd favourites 1.60 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.