Out-of-sample track record
LONG
58.8% win rate
857W600L
SHORT
59.2% win rate
251W173L
COMBINED
58.9% win rate
1108W773L
Skill & risk — beyond the headline win rate
Selection edge
Win rate of the top-1% signals minus the win rate of taking every bar
(baseline L 42.7% · S 44.9%).
It isolates how much the model's ranking adds.
Drawdown & streak Max drawdown = the deepest peak-to-trough of the Σ (win − loss) curve;
longest losing streak = the most consecutive SL-first calls. Both counted in
calls, never in money.
Cumulative correct calls (Σ win − loss · unitless)
Calibration — does higher conviction mean higher accuracy?
Signals grouped into expanding-window conviction tiers — the same live-honest ranking the model applies. Lower tiers sit near the coin-flip baseline; the edge is concentrated in the extreme tail. The outlined top 1% bar is exactly the slice the model selects, and it clears 50% on both sides.
LONG · win rate by conviction band
SHORT · win rate by conviction band
Monthly win rate (top-1%, decided)