Accuracy

Every gameweek's projections are frozen at the deadline and scored against what actually happened — next to FPL's own expected points, frozen at the same moment. No retro-fitting: once a deadline passes, the frozen file can't be touched.

Rank quality (Spearman)

0.38

FPL ep_next 0.24

Beat FPL's projection

4 of 4

gameweeks, by rank quality

Captain call, pts/GW

9.8

hindsight best 18.0 · FPL 7.3

Points error (RMSE)

2.17

FPL 2.43 · lower is better

Rank quality per gameweek

FPL PalFPL ep_next

GW1

0.24

0.16

GW2

0.50

0.26

GW3

0.36

0.20

GW4

0.40

0.35

Spearman correlation between projected and realized points among players who played, within each position. 1 would be a perfect ordering; typical good weeks live around 0.3–0.4.

GW	Fixtures	Rank corr	FPL	RMSE	FPL	Captain call	xPts vs actual
GW1	10	0.24	0.16	2.55	2.63	Fernandes 2 · best 17	-15%
GW2	10	0.50	0.26	2.06	2.38	Fernandes 23 · best 23	-1%
GW3	10	0.36	0.20	1.87	2.41	Haaland 9 · best 15	-3%
GW4	10	0.40	0.35	2.15	2.28	Palmer 5 · best 17	-5%

Under the hood, one gameweek at a time

Loading the gameweek…

How this is measured

Frozen at the deadline. After every nightly refresh, the engine writes each upcoming gameweek's projections to a frozen file — and refuses to touch that file once the gameweek's deadline has passed. What gets scored is exactly what this site was serving when the deadline hit.

Scored when final. A gameweek is scored only after FPL marks it finished and data-checked (bonus confirmed). Double-gameweek players are compared on their full week; fixtures postponed out of a gameweek are excluded and disclosed in the fixtures column, never quietly dropped.

The baselines. FPL publishes its own expected points (ep_next) — it's frozen at the same deadline and scored the same way. Rank correlation is measured within each position among players who actually played; RMSE counts everyone projected, including the ones who never left the bench.

season 2026-27 · scored 2026-09-16 01:15 · latest freeze 2026-09-15 02:31