Skip to content
FPLRogueResearch
Settled result review

FPL GW7 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.

Snapshot2026-10-16-gw7
Likely players259
Likely-player MAE2.60 pts
xMins MAE23.6 min
No post-result reconstruction

Accuracy by cohort

CohortPlayersMAERMSEBiasWithin 2 ptsxMins MAEStart Brier
All captured players6671.342.15+0.4371.2%14.4 min0.115
Projected ≥45 minutes2592.603.12+0.8939.0%23.6 min0.199
Predicted top 25253.503.92+1.5920.0%14.3 min0.155
Highest pre-deadline xPts

Predicted top 10 outcomes

PlayerTeamPredictedActualErrorxMinsMinutes
#1 HaalandMCI10.1813-2.8286.090
#2 CherkiMCI6.710+6.7165.80
#3 SakaARS6.293+3.2987.090
#4 B.FernandesMUN6.151+5.1587.090
#5 GuéhiMCI6.151+5.1587.990
#6 GroßBHA5.925+0.9287.070
#7 SemenyoMCI5.811+4.8187.013
#8 De CuyperBHA5.736-0.2787.090
#9 VuskovicBHA5.4911-5.5187.090
#10 CalafioriARS5.476-0.5387.090

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.