Every prediction, graded
Onside v0.5 predicts a player’s gameweek score to within 0.86 points on average, measured across 51,518 out-of-sample predictions. FPL’s own projection scores 0.896 on the same measure. Lower is better.
| Model | MAE | |
|---|---|---|
| Onside v5 | 0.860 | This model |
| FPL's own ep_next | 0.896 | The official projection |
| Onside v2 (closed form) | 1.025 | Our previous engine |
| Form, last 4 GWs | 1.048 | Naive baseline |
| Season mean | 1.054 | Naive baseline |
| Onside v1 (legacy) | 1.208 | Where we started |
Beats a recent-form baseline in 76.5% of gameweeks, and the v1 legacy engine in 100%.
What this number is, precisely
Accuracy claims are only worth as much as their definition, so here is ours. MAE is measured out-of-sample — the model never saw these gameweeks during training. Predictions are timestamped before kickoff and are never revised afterwards. The figure above is the validated-population measure; the ledger behind it is public, and the methodology page sets out how the grading works.
One honest caveat about the comparison: FPL’s ep_next has information advantages ours does not, so treat 0.896 as a reference point rather than a defeated opponent.
Questions
How accurate are Onside FPL predictions?
Onside v0.5 scores a mean absolute error of 0.86 points per player per gameweek across 51,518 out-of-sample predictions. For comparison, FPL's own ep_next scores 0.896 and a naive "recent form" baseline scores 1.048. Lower is better.
What does MAE mean in FPL?
Mean absolute error is the average gap between a predicted score and the actual score, in FPL points. An MAE of 0.86 means the projection is off by about nine-tenths of a point per player per gameweek on average. It is the standard way to grade a points model, and it cannot be gamed by only predicting easy cases — every prediction counts.
Which FPL prediction tool is the most accurate?
It is not currently possible to say, because almost nobody publishes a graded record. Competing tools advertise accuracy without a scoreboard behind it. Onside publishes this page and the full prediction ledger so the claim can be checked rather than taken on trust.
Is the accuracy figure independently verifiable?
The predictions are timestamped before kickoff and the results are public, so the record can be recomputed by anyone. Predictions are never revised after the fact.