GW6 forecast report
The GW6 forecast published before the deadline, scored against official FPL points. The forecast baseline stays fixed when the model changes later.
Scored against official GW6 results using the published pre-deadline projection export generated 23 Sep 2026. This forecast is preserved as a historical record and cannot be rewritten by later model updates.
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 1.23 pts.
Against a flat 2-point guess
Both rows use the same 315 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 | 68.9% | 1.88 | 2.89 | +0.64 |
| Always forecast 2 | 78.7% | 1.90 | 3.00 | +0.85 |
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. 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 | 37 | 3.70 | 1.35 | +2.35 | 9/10 |
| Top 20 | 62 | 3.10 | 1.35 | +1.75 | 18/20 |
| Top 50 | 153 | 3.06 | 1.35 | +1.71 | 45/50 |
By position
| Position | Avg miss | Bias | Within 2 |
|---|---|---|---|
| Goalkeepers | 1.93 | −0.36 | 65.0% |
| Defenders | 1.87 | +0.39 | 64.5% |
| Midfielders | 1.89 | +0.88 | 71.1% |
| Forwards | 1.79 | +0.95 | 74.4% |
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 | 5.4 | 6 | +0.6 |
| Thiago | FWD | 3.9 | 4 | +0.1 |
| Thomas | DEF | 3.6 | 4 | +0.4 |
| Mitchell | DEF | 3.6 | 4 | +0.4 |
| Richards | DEF | 3.4 | 4 | +0.6 |
| Iwobi | MID | 3.3 | 4 | +0.7 |
| Buendía | MID | 3.1 | 4 | +0.9 |
| Gvardiol | DEF | 3.0 | 4 | +1.0 |
| Canvot | DEF | 2.9 | 4 | +1.1 |
| Garner | MID | 2.5 | 4 | +1.5 |
Largest misses
| Player | Pos | Forecast | Actual | Miss |
|---|---|---|---|---|
| Henderson | MID | 1.3 | 18 | 16.7 |
| De Cuyper | DEF | 3.3 | 15 | 11.7 |
| Cherif | FWD | 1.2 | 12 | 10.8 |
| Doku | MID | 1.3 | 12 | 10.7 |
| Dewsbury-Hall | MID | 3.6 | 13 | 9.4 |
| João Pedro | FWD | 3.0 | 12 | 9.0 |
| Ouattara | DEF | 1.5 | 10 | 8.5 |
| O'Shea | DEF | 3.1 | 11 | 7.9 |
| Lerma | MID | 0.9 | 8 | 7.1 |
| McGinn | MID | 3.0 | 10 | 7.0 |
| Bruno G. | MID | 2.1 | 9 | 6.9 |
| Gelhardt | MID | 1.2 | 8 | 6.8 |
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
- Training window
- Results through GW5; GW4–GW5 walk-forward validation.
- Published
- 23 Sept 2026, 01:49 UTC, before the deadline
- Report generated
- 13 Oct 2026, 15:16 UTC
- Points source
- Official FPL event 6 live and fixtures feeds
- Result status
- 10 of 10 fixtures provisionally finished when scored
- Snapshot fingerprint
- bc3494505fafc078c3244d374a8852e1377cf760de20af539f3b10b3098c5945
This report is historical evidence for GW6, not a test of the current model. See the live GW10 forecasts.