GW7 forecast report
A reconstructed GW7 forecast scored against official FPL points. The forecast baseline stays fixed when the model changes later.
Original GW7 pre-deadline forecast and checkpoint are unavailable. This fixed audit baseline was reconstructed after the deadline from data through GW6 and must not be described as the published GW7 prediction. The fixed audit fingerprint is a1b9ab9a8d206542e920d1370a40f73300b9802db49972a8c7731fe34fafaf66. FPL has marked every fixture finished.
Headline figures cover only players who played, since forecasting zero for a benched player is easy and would flatter the numbers. Across all 667 players the average miss was 1.59 pts.
Against a flat 2-point guess
Both rows use the same 304 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 | 68.4% | 1.91 | 2.80 | +0.47 |
| Always forecast 2 | 75.3% | 1.96 | 3.06 | +0.91 |
How the xPts rankings performed
Top picks are ranked by forecast xPts. Actual averages include zero-minute picks; the field average uses the same 667 forecasted players. GW7 is reconstructed after the deadline, so treat this as audit-only selection signal, not a pre-deadline result.
| Highest xPts | Total actual | Avg per pick | Field avg / player | Uplift / pick | Played |
|---|---|---|---|---|---|
| Top 10 | 47 | 4.70 | 1.33 | +3.37 | 10/10 |
| Top 20 | 82 | 4.10 | 1.33 | +2.77 | 19/20 |
| Top 50 | 187 | 3.74 | 1.33 | +2.41 | 48/50 |
By position
| Position | Avg miss | Bias | Within 2 |
|---|---|---|---|
| Goalkeepers | 2.08 | −0.02 | 57.1% |
| Defenders | 2.11 | +0.55 | 59.6% |
| Midfielders | 1.71 | +0.36 | 75.0% |
| Forwards | 2.04 | +0.95 | 74.3% |
Closest calls in the reconstruction
High-output players scoring at least 4 points where the reconstructed baseline was within 1.5 points. These are not the original GW deadline calls.
| Player | Pos | Forecast | Actual | Gap |
|---|---|---|---|---|
| Groß | MID | 4.2 | 5 | +0.8 |
| Muharemović | DEF | 3.6 | 5 | +1.4 |
| Van Hecke | DEF | 3.7 | 4 | +0.3 |
| Hall | DEF | 3.7 | 4 | +0.3 |
| E.Le Fée | MID | 3.6 | 4 | +0.4 |
| Thiago | FWD | 3.6 | 4 | +0.4 |
| Tonali | MID | 3.2 | 4 | +0.8 |
| Egan | DEF | 3.1 | 4 | +0.9 |
| Virgil | DEF | 3.0 | 4 | +1.0 |
| Maguire | DEF | 2.9 | 4 | +1.1 |
| Schlager | MID | 2.8 | 4 | +1.2 |
Largest misses
| Player | Pos | Forecast | Actual | Miss |
|---|---|---|---|---|
| Neto | MID | 2.9 | 15 | 12.1 |
| Ayari | MID | 3.1 | 13 | 9.9 |
| Manzambi | MID | 2.0 | 11 | 9.0 |
| Hato | DEF | 2.0 | 11 | 9.0 |
| Kostoulas | FWD | 3.1 | 12 | 8.9 |
| Evanilson | FWD | 3.2 | 12 | 8.8 |
| Maddison | MID | 1.2 | 9 | 7.8 |
| Iwobi | MID | 3.3 | 11 | 7.7 |
| Haaland | FWD | 5.3 | 13 | 7.7 |
| Vuskovic | DEF | 3.8 | 11 | 7.2 |
| Boscagli | DEF | 3.1 | 10 | 6.9 |
| Konsa | DEF | 2.4 | 9 | 6.6 |
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
- 1.4.0
- Forecast source
- Reconstructed after the deadline
- Training window
- Results through GW6; Not a recovered deadline forecast; neutral availability and no historical news/market snapshot..
- Reconstruction locked
- 20 Oct 2026, 03:54 UTC
- Report generated
- 20 Oct 2026, 08:36 UTC
- Points source
- https://fantasy.premierleague.com/api/event/7/live/
- Result status
- 10 of 10 fixtures provisionally finished when scored
- Snapshot fingerprint
- a1b9ab9a8d206542e920d1370a40f73300b9802db49972a8c7731fe34fafaf66
This report is historical evidence for GW7, not a test of the current model. See the live GW10 forecasts.