GW5 forecast report
The GW5 forecast published before the deadline, scored against official FPL points. The forecast baseline stays fixed when the model changes later.
Official GW5 results scored against the published pre-deadline forecast. The original forecast fingerprint is c6a9aa57a720d5f2868aaf1b31fec5c2ca5044e2c9a6e99b7f2b0191ac09f15a.
Headline figures cover only players who played, since forecasting zero for a benched player is easy and would flatter the numbers. Across all 659 players the average miss was 1.26 pts.
Against a flat 2-point guess
Both rows use the same 301 players who recorded minutes. A hit-rate can hide how far misses are, so compare average miss and RMSE too.
| Forecast | Within 2 | Avg miss | RMSE | Bias |
|---|---|---|---|---|
| FPL Prism | 69.1% | 1.96 | 3.03 | +0.78 |
| Always forecast 2 | 74.8% | 2.08 | 3.33 | +1.21 |
How the xPts rankings performed
Top picks are ranked by forecast xPts. Actual averages include zero-minute picks; the field average uses the same 659 forecasted players. This is selection signal from the frozen forecast pool, not a guaranteed squad result.
| Highest xPts | Total actual | Avg per pick | Field avg / player | Uplift / pick | Played |
|---|---|---|---|---|---|
| Top 10 | 35 | 3.50 | 1.46 | +2.04 | 10/10 |
| Top 20 | 105 | 5.25 | 1.46 | +3.79 | 20/20 |
| Top 50 | 238 | 4.76 | 1.46 | +3.30 | 49/50 |
By position
| Position | Avg miss | Bias | Within 2 |
|---|---|---|---|
| Goalkeepers | 2.58 | +1.08 | 50.0% |
| Defenders | 2.32 | +1.10 | 59.8% |
| Midfielders | 1.73 | +0.61 | 75.0% |
| Forwards | 1.58 | +0.41 | 80.6% |
Best calls
High-output players scoring at least 4 points where the pre-deadline forecast was within 1.5 points of the official result.
| Player | Pos | Forecast | Actual | Gap |
|---|---|---|---|---|
| Haaland | FWD | 6.0 | 6 | +0.0 |
| Thiago | FWD | 4.2 | 5 | +0.8 |
| Stach | MID | 4.0 | 5 | +1.0 |
| E.Le Fée | MID | 3.8 | 5 | +1.2 |
| Bogle | DEF | 3.7 | 5 | +1.3 |
| Ampadu | MID | 3.6 | 5 | +1.4 |
| Thiaw | DEF | 3.9 | 4 | +0.1 |
| Murillo | DEF | 3.9 | 4 | +0.1 |
| Guéhi | DEF | 4.2 | 4 | -0.2 |
| Gvardiol | DEF | 3.6 | 4 | +0.4 |
| Lammens | GKP | 3.4 | 4 | +0.6 |
| Botman | DEF | 3.3 | 4 | +0.7 |
Largest misses
| Player | Pos | Forecast | Actual | Miss |
|---|---|---|---|---|
| Brobbey | FWD | 2.5 | 17 | 14.5 |
| Semenyo | MID | 3.9 | 17 | 13.1 |
| Dasilva | DEF | 2.6 | 15 | 12.4 |
| Schuster | DEF | 1.8 | 14 | 12.2 |
| Manzambi | MID | 1.3 | 13 | 11.7 |
| Groß | MID | 3.8 | 14 | 10.2 |
| Tarkowski | DEF | 4.1 | 14 | 9.9 |
| Hall | DEF | 3.4 | 13 | 9.6 |
| Buendía | MID | 2.8 | 12 | 9.2 |
| Willock | MID | 1.6 | 10 | 8.4 |
| Rushworth | GKP | 3.2 | 11 | 7.8 |
| Anthony | MID | 2.4 | 10 | 7.6 |
What these measures mean
- Average miss (MAE): the typical gap between forecast and actual points, ignoring direction.
- RMSE: like the average miss, but big misses count for more.
- Bias: actual minus forecast on average. Positive means players outscored their forecasts.
- Within 2: share of players whose actual score was within 2 points of the forecast.
Snapshot and data source
- Model version
- 1.3.0
- Forecast source
- Published pre-deadline export
- Report generated
- 20 Sept 2026, 20:02 UTC
- Points source
- Official FPL event 5 live and fixtures feeds
- Result status
- 10 of 10 fixtures provisionally finished when scored
- Snapshot fingerprint
- c6a9aa57a720d5f2868aaf1b31fec5c2ca5044e2c9a6e99b7f2b0191ac09f15a
This report is historical evidence for GW5, not a test of the current model. See the live GW10 forecasts.