AI Predictions

Poisson match modelling and expected points, computed on the server

ID 1900182 –

Prediction engine active • computed on the server

Gameweek 1 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 1 Next

Match Outcomes

10 Fixtures

Friday 21 August

Arsenal
20:00
Coventry City
74% 17% draw 9%
2.30 xG Arsenal strong favourites 0.68 xG

Saturday 22 August

Hull City
12:30
Man Utd
24% 24% draw 52%
1.03 xG Man Utd favourites 1.66 xG
Everton
15:00
Crystal Palace
48% 25% draw 27%
1.59 xG Everton favourites 1.13 xG
Ipswich Town
15:00
Sunderland
34% 26% draw 40%
1.30 xG Sunderland favourites 1.42 xG
Nott'm Forest
15:00
Leeds
49% 24% draw 26%
1.65 xG Nott'm Forest favourites 1.13 xG
Brentford
17:30
Spurs
48% 25% draw 27%
1.59 xG Brentford favourites 1.13 xG

Sunday 23 August

Brighton
14:00
Aston Villa
26% 25% draw 49%
1.10 xG Aston Villa favourites 1.61 xG
Man City
14:00
Bournemouth
64% 21% draw 14%
1.94 xG Man City strong favourites 0.79 xG
Newcastle
16:30
Liverpool
24% 25% draw 51%
1.03 xG Liverpool favourites 1.61 xG

Monday 24 August

Fulham
20:00
Chelsea
24% 25% draw 51%
1.03 xG Chelsea favourites 1.61 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.