DetectorKilled

Trade the forced sell-off at the squeeze moment

+1.12 bps

average return on fresh data, not statistically real, and 10× weaker than in testing

bps = basis points = a hundredth of a percent (100 bps = 1%).

In plain English

Betting that forced sell-offs keep falling worked in old data but fell apart on fresh data, the effect shrank tenfold and flipped direction.

What it needed

> ~18 bps after cost, stable out-of-sample

→

What it got

+1.12 bps, not statistically significant, 10× weaker than in testing

Why it's dead

A real mechanism, HLP vault forcibly closes positions during cascades, that completely failed to survive a clean OOS split. The in-sample magnitude collapsed 10× and the signal flipped sign on fresh data.

The detail

OOS holdout Mar 18–25. Exploratory (in-sample) signal: −11.95 bps mean at 5m. OOS mean: +1.12 bps, p=0.449, not significant, and ~10× too small for the 18 bps cost hurdle even at face value. The collapse from in-sample to OOS is the classic overfitting signature.

Kill date: 2026-03-26
Sample: fresh data, Mar 18–25
Method: Pre-registered
Verdict: 10× in-sample collapse

Pre-registered before the data. Judged on a criterion locked in advance. Published whatever the result.

See all kills →