← Research logMachine Learning
PARTIAL · risk gate
#

An autoencoder trained on "normal" market states flags anomalous regimes (high reconstruction error) to step aside before disorderly moves.

$$ \text{anomaly}_t = \big\| \mathbf{x}_t - \text{Dec}(\text{Enc}(\mathbf{x}_t)) \big\|^2 $$

Train on calm-regime feature vectors, monitor reconstruction error live, de-risk on spikes.

Reconstruction error spikes pre-voloften
Lead timeshort / coincident
As a risk gatemildly useful
PARTIAL EDGE
A mild risk-gate: reconstruction error does rise around regime breaks, but mostly coincident with volatility, so it confirms more than it predicts. Kept as one input to a de-risking ensemble, not a trigger.
Anomaly detectors mostly tell you the present is unusual, not that the future is. Useful for stepping aside, weak for stepping in.

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.