FPL GW6 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.
Snapshot2026-10-10-gw6
Likely players254
Likely-player MAE2.43 pts
xMins MAE21.8 min
No post-result reconstruction
Accuracy by cohort
| Cohort | Players | MAE | RMSE | Bias | Within 2 pts | xMins MAE | Start Brier |
|---|---|---|---|---|---|---|---|
| All captured players | 667 | 1.22 | 2.10 | +0.31 | 75.6% | 12.7 min | 0.100 |
| Projected ≥45 minutes | 254 | 2.43 | 3.02 | +0.78 | 44.9% | 21.8 min | 0.180 |
| Predicted top 25 | 25 | 3.91 | 4.46 | +0.17 | 16.0% | 10.8 min | 0.056 |
Highest pre-deadline xPts
Predicted top 10 outcomes
| Player | Team | Predicted | Actual | Error | xMins | Minutes |
|---|---|---|---|---|---|---|
| #1 B.Fernandes | MUN | 8.34 | 1 | +7.34 | 87.4 | 90 |
| #2 Haaland | MCI | 7.19 | 6 | +1.19 | 87.5 | 79 |
| #3 Saka | ARS | 6.86 | 2 | +4.86 | 87.0 | 90 |
| #4 Mbeumo | MUN | 6.74 | 8 | -1.26 | 87.0 | 90 |
| #5 Hall | NEW | 5.85 | 0 | +5.85 | 87.4 | 90 |
| #6 Calafiori | ARS | 5.49 | 9 | -3.51 | 87.0 | 81 |
| #7 Gibbs-White | NFO | 5.49 | 2 | +3.49 | 87.0 | 90 |
| #8 Palmer | CHE | 5.42 | 8 | -2.58 | 87.0 | 87 |
| #9 Gabriel | ARS | 5.36 | 2 | +3.36 | 87.5 | 90 |
| #10 João Pedro | CHE | 5.32 | 12 | -6.68 | 76.8 | 71 |
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.