Metis·FootballFPL · Track record

FPL projection accuracy & track record.

3 gameweeks settled

Model updated

Across 3 settled gameweeks and 960 player-projections, Metis projections miss by 1.89 points per player on average, with an overall bias of +0.10 (actual minus projected) and a rank correlation of 0.57 between projected and actual points.

The projection of record for each gameweek is the last nightly publish before that deadline — never a later one. Actual points are joined from the official feed once the gameweek finishes, and every miss is published exactly like every hit.

Mean abs error

1.89

points per player

Bias

+0.10

actual − projected

Rank correlation

0.57

Spearman, projected vs actual

Top-20 projected

6.0 → 4.3

projected → actual, mean

By gameweek

Every settled gameweek

Gameweek pages
GWPlayersMAEBiasRMSESpearmanTop 20 proj → actFantasy 11 proj → act
GW3locked Fri 4 Sept3201.80+0.042.570.555.23.55.13.8
GW4locked Sat 12 Sept3202.05+0.042.940.545.45.34.94.3
GW5locked Fri 18 Sept3201.82+0.212.750.625.44.05.34.1

Calibration

Projected points vs what happened

Players grouped by projected points (all settled gameweeks pooled). A well-calibrated model shows the actual mean tracking the projected mean in every bin.

Calibration by projected points
SegmentPlayersProjectedActualBiasMAE
0–1 xPts2200.320.53+0.210.47
1–2 xPts1141.521.60+0.091.40
2–3 xPts2422.552.57+0.022.05
3–4 xPts2463.463.61+0.152.45
4–5 xPts1034.374.89+0.533.26
5–6 xPts295.463.86-1.603.20
6–8 xPts56.545.00-1.544.36
8+ xPts18.326.00-2.322.32

Start probability

Did they actually play?

Start probabilities
Start probability binPlayersMean start%AppearedPlayed 60+
0–25%2525%33%9%
25–50%8539%78%33%
50–70%9360%91%77%
70–85%10477%90%74%
85–95%15992%92%81%
95–100%26797%97%92%

"Played 60+" is the closest official proxy for a start; the feed does not publish lineups retrospectively.

Breakdown

By position and price

Accuracy by position
SegmentPlayersProjectedActualBiasMAE
GK1201.642.00+0.361.35
DEF3322.472.76+0.292.18
MID4112.592.52-0.081.73
FWD972.882.74-0.142.23
Accuracy by price band
SegmentPlayersProjectedActualBiasMAE
≤£5.0m4822.072.23+0.161.69
£5.1–7.0m4172.682.71+0.022.00
£7.1–9.5m523.714.12+0.412.69
£9.6m+95.834.22-1.612.78

Squads

Fantasy 11 and Metis FC, projected vs actual

Metis FC
GWFantasy 11 projactualMetis FC projactualGW average
GW566.95164.14848
GW461.25960.95369
GW363.45662.54551
GW253.310181
GW14350

Method

How this is scored

  • Every nightly publish snapshots all projected players. The projection of record for a gameweek is the last snapshot before its deadline; later snapshots are never scored.
  • Actual points and minutes come from the official FPL event feed once the gameweek is flagged finished. Nothing is re-projected after the fact.
  • MAE is the mean absolute error in points per player; bias is actual minus projected (positive means the model under-projected); Spearman is the rank correlation between projected and actual points over the whole pool.
  • Expected points are a mean over a right-skewed distribution: a single player's actual score is usually far from their xPts, so per-player error is large by construction. Calibration — whether groups of players score what they were projected on average — is the fairer test.
  • Players outside the projected pool (not published) are not scored either way.

Last updated 23 Sep · 04:07 UTC