WWCFxWorld Cup Fantasy Advanced Model
Matchday12345678
Backtest · Matchday 5

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
248
Mean abs error
2.42
pts/player
Rank correlation
0.30
predicted vs actual
Bias
+0.13
over-predict
Scouting-bonus calibration

predicted chance to clear threshold vs what actually happened

BucketPredictedObservedn
0-20%11%8%108
20-40%29%27%77
40-60%48%46%11
Recommended XI · actual result
XI actual points (capt ×2)
72.0
Captain
Ousmane Dembélé (3 pts)
Captain rank in XI
#8 of 11
Best captain (hindsight)
Lionel Messi
Avg player (field)
3.22 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+0.25
pred 2.56 · actual 2.31 · n=124
1-5% owned-0.19
pred 3.91 · actual 4.1 · n=72
5-15% owned+0.04
pred 3.71 · actual 3.68 · n=31
15%+ owned+0.65
pred 5.6 · actual 4.95 · n=21
Biggest prediction misses
MIDCharles De Ketelaere
pred 2.9 · actual 19
MIDAzzedine Ounahi
pred 3 · actual 16
MIDJude Bellingham
pred 5 · actual 15
MIDHans Vanaken
pred 4.2 · actual 13
MIDOusmane Dembélé
pred 11.6 · actual 3
FWDErling Haaland
pred 5.1 · actual 13
MIDBrahim Díaz
pred 4.5 · actual 12
DEFYasser Ibrahim
pred 1.7 · actual 9
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
72
capt Ousmane Dembélé (3) · best: Lionel Messi
Balanced
72
capt Ousmane Dembélé (3) · best: Lionel Messi
Wildcard
63
capt Ousmane Dembélé (3) · best: Lionel Messi
Scouting Bonus
61
capt Bradley Barcola (2) · best: Gregor Kobel
Maximum Points
52
capt Ousmane Dembélé (3) · best: Lionel Messi
Best possible XI
155
formation-legal, whole pool
Best legal squad XI
155
budget + country limits respected
Field-average XI
~38.6
random valid team benchmark
Under-projected · what we missed
  • MIDCharles De Ketelaere2.919

    Scored 19 largely through tackle/chance volume the per-90 rates didn't credit (model expected 0.6 pts from those routes).

  • MIDAzzedine Ounahi316

    Scored 16 largely through tackle/chance volume the per-90 rates didn't credit (model expected 0.5 pts from those routes).

  • MIDJude Bellingham515

    Low goal prior (24%) but hauled 15 — likely a finishing spike. Check role support before chasing.

  • MIDHans Vanaken4.213

    Low goal prior (3%) but hauled 13 — likely a finishing spike. Check role support before chasing.

  • FWDErling Haaland5.113

    Returned 13 vs 5.1 projected — team/fixture strength for this matchup was likely underrated.

  • MIDBrahim Díaz4.512

    Scored 12 largely through tackle/chance volume the per-90 rates didn't credit (model expected 0.5 pts from those routes).

Over-projected · what we chased
  • MIDOusmane Dembélé11.63

    Played but blanked (3 vs 11.6 projected) — mostly variance.

  • MIDBradley Barcola8.62

    Ceiling pick projected 8.6 but returned 2. High-variance blank; the miss cost is amplified if captained.

  • MIDVinícius Júnior8.42

    Ceiling pick projected 8.4 but returned 2. High-variance blank; the miss cost is amplified if captained.

  • DEFAlexander Freeman5-1

    Projected 73 minutes but recorded 0 points — benched, unused or the round hadn't scored him. Start model called this wrong.

  • FWDCyle Larin5.30

    Projected 73 minutes but recorded 0 points — benched, unused or the round hadn't scored him. Start model called this wrong.

  • DEFJorge Sánchez4-1

    Projected 74 minutes but recorded 0 points — benched, unused or the round hadn't scored him. Start model called this wrong.

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

backtested 4 Aug, 08:15 UTC