FPL GW9 projection accuracy scorecard
The accepted xpts_v1 release was frozen before the deadline, then compared with official points, minutes and starts after the Gameweek finished.
Snapshot2026-10-31-gw9
Likely players222
Likely-player MAE2.31 pts
xMins MAE18.3 min
No post-result reconstruction
Accuracy by cohort
| Cohort | Players | MAE | RMSE | Bias | Within 2 pts | xMins MAE | Start Brier |
|---|---|---|---|---|---|---|---|
| All captured players | 669 | 1.18 | 1.94 | +0.36 | 75.5% | 12.5 min | 0.084 |
| Projected ≥45 minutes | 222 | 2.31 | 2.79 | +0.62 | 46.4% | 18.3 min | 0.128 |
| Predicted top 25 | 25 | 3.32 | 3.90 | -0.05 | 20.0% | 14.2 min | 0.077 |
Highest pre-deadline xPts
Predicted top 10 outcomes
| Player | Team | Predicted | Actual | Error | xMins | Minutes |
|---|---|---|---|---|---|---|
| #1 Haaland | MCI | 7.71 | 2 | +5.71 | 86.1 | 90 |
| #2 N.Jackson | AVL | 5.73 | 9 | -3.27 | 85.7 | 90 |
| #3 Tavernier | BOU | 5.56 | 3 | +2.56 | 85.8 | 90 |
| #4 Gabriel | ARS | 5.46 | 6 | -0.54 | 88.3 | 90 |
| #5 Doku | MCI | 5.15 | 2 | +3.15 | 81.7 | 90 |
| #6 Mbeumo | MUN | 5.05 | 1 | +4.05 | 85.8 | 90 |
| #7 B.Fernandes | MUN | 5.04 | 2 | +3.04 | 68.2 | 90 |
| #8 E.Le Fée | SUN | 4.92 | 8 | -3.08 | 85.8 | 90 |
| #9 Gibbs-White | NFO | 4.78 | 2 | +2.78 | 68.3 | 90 |
| #10 Van Hecke | TOT | 4.63 | 15 | -10.37 | 87.7 | 90 |
How this scorecard is calculated
Point error is predicted next-Gameweek xPts minus settled official points. MAE averages absolute error; RMSE gives larger misses more weight; positive bias means overprediction. Minutes MAE compares xMins with played minutes. Start Brier score measures the probability forecast against the official start flag, where lower is better.