sweep: match.total_cards >= 3
← lab · AUC 0.563 (weak signal) · ran 7/4/2026
What this is: Asks which pre-match factors drive one specific outcome, using a walk-forward model and permutation importance.
| Factor | Importance | Direction | Survives all eras? |
|---|
| home__team.cards_avg_l5 | 0.0019 | ↑ +0.075 | ⏳ yes |
| ratio__team.elo | 0.0019 | ↓ -0.045 | ⏳ yes |
| away__team.cards_avg_l5 | 0.0016 | ↑ +0.076 | ⏳ yes |
| market.p_draw | 0.0015 | ↑ +0.046 | ⏳ yes |
| match.stakes | 0.0014 | ↓ -0.029 | ⏳ yes |
| away__team.congestion_21d | 0.0014 | ↓ -0.044 | ⏳ yes |
| x__match.ref_fouls_avg__match.style_clash_corners | 0.0013 | ↓ -0.003 | no |
| x__home__team.goals_for_avg_l5__away__team.defensive_leak_l5 | 0.0012 | ↓ -0.020 | no |
| match.momentum_clash | 0.0011 | ↓ -0.006 | no |
| home__team.matches_since_blank | 0.0011 | ↑ +0.000 | no |
| market.p_home | 0.0011 | ↓ -0.044 | ⏳ yes |
| home__team.dominance_l5 | 0.0010 | ↓ -0.002 | no |
Reading the columnswhat each number actually means
| AUC | predictability: 0.50 = coin flip, ~0.70 = ceiling for sports |
| Importance | how much the model leans on this factor (permutation importance) |
| Direction | sign of the raw correlation with the outcome |
| Survives all eras | effect points the same way in every historical era |
Spec · the reproducible recipe
{
"name": "sweep: match.total_cards >= 3",
"sport": "football",
"target": {
"op": ">=",
"value": 3,
"metric": "match.total_cards"
},
"features": "all"
}