sweep: match.btts (bool)

← lab · AUC 0.512 (no real pattern — honest result) · 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.ht_lead_rate_l20	0.0043	↓ -0.010	no
diff__team.goal_diff_avg_l5	0.0024	↓ -0.023	⏳ yes
home__t3__team.shots_for_avg_l5	0.0022	↑ +0.002	no
away__t3__team.corners_volatility_l10	0.0020	↓ -0.003	no
market.p_draw	0.0019	↑ +0.032	no
market.overround_1x2	0.0019	↓ -0.008	no
match.style_clash_corners	0.0018	↓ -0.002	no
ratio__team.ht_lead_rate_l20	0.0016	↓ -0.018	no
market.p_over25	0.0015	↑ +0.050	⏳ yes
diff__team.corner_diff_avg_l5	0.0015	↓ -0.022	⏳ yes
diff__team.corners_volatility_l10	0.0014	↓ -0.011	no
ratio__team.h2h_win_rate_l5	0.0013	↓ -0.028	⏳ yes

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.btts (bool)",
  "sport": "football",
  "target": {
    "metric": "match.btts"
  },
  "features": "all"
}