FPL GW8 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.
Snapshot2026-10-23-gw8
Likely players223
Likely-player MAE2.66 pts
xMins MAE21.2 min
No post-result reconstruction
Accuracy by cohort
| Cohort | Players | MAE | RMSE | Bias | Within 2 pts | xMins MAE | Start Brier |
|---|---|---|---|---|---|---|---|
| All captured players | 668 | 1.33 | 2.19 | +0.29 | 72.8% | 13.9 min | 0.105 |
| Projected ≥45 minutes | 223 | 2.66 | 3.20 | +0.67 | 36.8% | 21.2 min | 0.167 |
| Predicted top 25 | 25 | 4.21 | 4.81 | +1.65 | 20.0% | 21.1 min | 0.159 |
Highest pre-deadline xPts
Predicted top 10 outcomes
| Player | Team | Predicted | Actual | Error | xMins | Minutes |
|---|---|---|---|---|---|---|
| #1 Haaland | MCI | 7.70 | 8 | -0.30 | 86.1 | 90 |
| #2 B.Fernandes | MUN | 6.57 | 0 | +6.57 | 86.0 | 0 |
| #3 Mbeumo | MUN | 6.13 | 2 | +4.13 | 85.9 | 90 |
| #4 Calafiori | ARS | 6.08 | 1 | +5.08 | 85.8 | 22 |
| #5 Gabriel | ARS | 5.97 | 17 | -11.03 | 88.2 | 90 |
| #6 João Pedro | CHE | 5.80 | 0 | +5.80 | 65.9 | 0 |
| #7 Palmer | CHE | 5.72 | -1 | +6.72 | 85.9 | 79 |
| #8 Rogers | CHE | 5.13 | 1 | +4.13 | 85.8 | 90 |
| #9 Konsa | ARS | 5.07 | 14 | -8.93 | 86.6 | 90 |
| #10 Doku | MCI | 4.98 | 2 | +2.98 | 75.7 | 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.