FPL GW5 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.
Snapshot2026-09-18-gw5
Likely players289
Likely-player MAE2.63 pts
xMins MAE24.5 min
No post-result reconstruction
Accuracy by cohort
| Cohort | Players | MAE | RMSE | Bias | Within 2 pts | xMins MAE | Start Brier |
|---|---|---|---|---|---|---|---|
| All captured players | 659 | 1.51 | 2.36 | +0.56 | 68.1% | 16.3 min | 0.111 |
| Projected ≥45 minutes | 289 | 2.63 | 3.28 | +0.75 | 37.7% | 24.5 min | 0.203 |
| Predicted top 25 | 25 | 3.77 | 4.45 | +1.78 | 24.0% | 13.2 min | 0.093 |
Highest pre-deadline xPts
Predicted top 10 outcomes
| Player | Team | Predicted | Actual | Error | xMins | Minutes |
|---|---|---|---|---|---|---|
| #1 Haaland | MCI | 9.00 | 6 | +3.00 | 87.6 | 90 |
| #2 Gibbs-White | NFO | 7.20 | 2 | +5.20 | 88.6 | 90 |
| #3 B.Fernandes | MUN | 7.16 | 2 | +5.16 | 86.3 | 90 |
| #4 Muñoz | NFO | 6.66 | 2 | +4.66 | 80.7 | 82 |
| #5 Cherki | MCI | 6.52 | 8 | -1.48 | 81.9 | 84 |
| #6 N.Williams | NFO | 6.35 | 2 | +4.35 | 89.1 | 90 |
| #7 Guéhi | MCI | 6.12 | 4 | +2.12 | 89.3 | 90 |
| #8 Diomande | NFO | 5.92 | 2 | +3.92 | 71.5 | 72 |
| #9 O'Reilly | MCI | 5.81 | 1 | +4.81 | 75.1 | 5 |
| #10 Saka | ARS | 5.56 | 2 | +3.56 | 71.6 | 80 |
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.