⚽ Tomulator
Overview
β—ˆDashboardπŸ“…Today's gamesβ—ŽState of play
Money
πŸ’·Bets & strategies
Explore
⊞Leagues & seasonsπŸ“Metricsβ–€Data sources
Engine room
🎲SimulationsπŸ§ͺLab≣Catalog?How this works

sure-thing survey

← lab Β· Β· ran 7/17/2026

What this is: A one-off study β€” its numbers below are exactly what the run reported.

cells

nbandwinsmarketroi pctavg priceselection
1,21870-80%901Match result-0.811.343away side win
2,98270-80%2,230Match result0.421.344home side win
47980-90%402Match result0.921.202away side win
2,08180-90%1,739Match result-0.931.187home side win
19p>=90%16Match result-8.411.088away side win
447p>=90%405Match result-1.651.086home side win
1,55770-80%1,107Over/Under 2.5 goals-3.71.357Over
39870-80%266Over/Under 2.5 goals-7.61.384Under
22280-90%186Over/Under 2.5 goals0.711.203Over
280-90%1Over/Under 2.5 goals-37.51.25Under
3p>=90%3Over/Under 2.5 goals10.51.105Over

Reading the columnswhat each number actually means

AUCpredictability: 0.50 = coin flip, ~0.70 = ceiling for sports
Importancehow much the model leans on this factor (permutation importance)
Directionsign of the raw correlation with the outcome
Survives all eraseffect points the same way in every historical era
Spec Β· the reproducible recipe
{
  "markets": [
    "1x2",
    "ou_goals_2_5",
    "btts"
  ],
  "threshold": ">=70% implied"
}