← Research logMachine Learning
PARTIAL · filter only
#

Gradient-boosted trees on engineered features (vol regime, funding, OI delta, time-of-day) can classify which signals of an existing book are higher-quality, used as a filter rather than a generator.

The model is an additive ensemble fit greedily to the gradient of the loss:

$$ \hat y = \sum_{m=1}^{M} \nu\, f_m(\mathbf{x}),\qquad f_m \approx -\nabla_{\hat y}\,\mathcal{L} $$

Label baseline signals win/loss, train XGBoost with monotonic constraints, evaluate as a probability gate on out-of-sample signals. Strict temporal split, no leakage.

AUC (out-of-sample)0.58
Top-quartile precision lift+9pp
Standalone generationno edge
Decay TRAIN→TESTmoderate
PARTIAL EDGE
Weak-but-real as a filter on an existing edge (AUC 0.58, top-quartile precision +9pp) — never as a signal generator. Most of the lift is the vol-regime and time-of-day features, not the exotic ones. Kept as an optional overlay with monitored decay.
ML earns its keep ranking the quality of signals you already have, not conjuring signals from price alone. And the boring features (regime, time) usually carry the lift.

We publish the failures too.

This is one of 100+ documented hypotheses. Browse the full lab notebook, or see the strategies that survived into production.