WWCFxWorld Cup Fantasy Advanced Model
Matchday12345678
Backtest · Matchday 7

Prediction Accuracy

After a round finishes, we score the predictions against actual fantasy points (FIFA feed) — error, ranking, scouting-bonus calibration, and how the recommended XI did. The hints feed back into tuning the model.

Model calibration · auto-tunedfrom rounds 1, 2, 3, 4, 5, 6, 7, 8

attacking-output multiplier the tuner learned per position (1.0 = no change)

GK×1.30
was under-predicting
DEF×1.30
was under-predicting
MID×1.14
was under-predicting
FWD×1.22
was under-predicting
Players scored
64
Mean abs error
2.40
pts/player
Rank correlation
0.13
predicted vs actual
Bias
+0.47
over-predict
Scouting-bonus calibration

predicted chance to clear threshold vs what actually happened

BucketPredictedObservedn
0-20%8%7%14
20-40%29%15%13
Recommended XI · actual result
XI actual points (capt ×2)
39.0
Captain
Kylian Mbappé (1 pts)
Captain rank in XI
#11 of 11
Best captain (hindsight)
Pedro Porro
Avg player (field)
2.84 pts
Predicted vs actual · by ownership bucket

where the model flatters players — chasing differentials is only right if the low-owned buckets aren't inflated

<1% owned+0.08
pred 2.08 · actual 2 · n=7
1-5% owned+0.78
pred 3.08 · actual 2.3 · n=20
5-15% owned+0.03
pred 3.41 · actual 3.38 · n=16
15%+ owned+0.65
pred 3.89 · actual 3.24 · n=21
Biggest prediction misses
DEFPedro Porro
pred 4 · actual 14
FWDKylian Mbappé
pred 7.6 · actual 1
MIDAnthony Gordon
pred 3.6 · actual 9
DEFReece James
pred 3.8 · actual 9
MIDEnzo Fernández
pred 2.9 · actual 8
MIDMorgan Rogers
pred 2.2 · actual 7
GKUnai Simón
pred 3.2 · actual 8
FWDLautaro Martínez
pred 3.2 · actual 8
Post-round autopsy · what actually happened

Every squad's real score vs the hindsight-best XIs, plus every big miss classified to the model factor that caused it — so each round makes the next projection better.

Recommended squad
39
capt Kylian Mbappé (1) · best: Pedro Porro
Maximum Points
37
capt Kylian Mbappé (1) · best: Pedro Porro
Wildcard
36
capt Kylian Mbappé (1) · best: Pedro Porro
Balanced
29
capt Kylian Mbappé (1) · best: Lionel Messi
Scouting Bonus
25
capt Aurélien Tchouaméni (3) · best: Lautaro Martínez
Your team
23
capt Kylian Mbappé (1) · best: Lionel Messi
Best possible XI
106
formation-legal, whole pool
Best legal squad XI
106
budget + country limits respected
Field-average XI
~34.1
random valid team benchmark
Under-projected · what we missed
  • DEFPedro Porro414

    DEF returned 14 vs 4.0 projected — clean-sheet/save/conceded points are systematically under-modelled for DEFs.

  • MIDAnthony Gordon3.69

    Scored 9 largely through tackle/chance volume the per-90 rates didn't credit (model expected 0.4 pts from those routes).

  • DEFReece James3.89

    DEF returned 9 vs 3.8 projected — clean-sheet/save/conceded points are systematically under-modelled for DEFs.

  • MIDEnzo Fernández2.98

    Scored 8 largely through tackle/chance volume the per-90 rates didn't credit (model expected 0.3 pts from those routes).

  • MIDMorgan Rogers2.27

    Returned 7 vs 2.2 projected — team/fixture strength for this matchup was likely underrated.

  • GKUnai Simón3.28

    GK returned 8 vs 3.2 projected — clean-sheet/save/conceded points are systematically under-modelled for GKs.

Over-projected · what we chased
  • FWDKylian Mbappé7.61

    Ceiling pick projected 7.6 but returned 1. High-variance blank; the miss cost is amplified if captained.

  • MIDOusmane Dembélé6.52

    Ceiling pick projected 6.5 but returned 2. High-variance blank; the miss cost is amplified if captained.

  • MIDBradley Barcola5.21

    Played but blanked (1 vs 5.2 projected) — mostly variance.

  • MIDJude Bellingham5.52

    Played but blanked (2 vs 5.5 projected) — mostly variance.

  • DEFMarcos Llorente4.31

    Played but blanked (1 vs 4.3 projected) — mostly variance.

  • FWDHarry Kane5.32

    Played but blanked (2 vs 5.3 projected) — mostly variance.

Model factors behind this round's misses
  • 6×Variance blank — played, no returns; only act if it repeats
  • 4×Team strength / fixture odds for this matchup
  • 3×Defensive scoring calibration (clean sheets, saves, conceded)
  • 2×Per-90 tackle / chance-created rates (volume routes)
  • 2×Ceiling pick blanked — captaincy/exposure sizing, not projection
  • 2×Start-probability model (predicted a start that didn't happen)
  • 1×Start-probability model (appearances / rotation signal)

backtested 4 Aug, 08:15 UTC