Market regime classification with signatures

TL;DR

This paper introduces a data-driven method for classifying market regimes in time series data using path signatures, which encode the data into manageable objects and relate regime separation to clustering.

Contribution

The paper presents a novel approach combining path signatures with a metric structure to classify market regimes effectively.

Findings

Path signatures enable effective encoding of time series.

The method links regime separation to clustering of signature representations.

The approach improves market regime classification accuracy.

Abstract

We provide a data-driven algorithm to classify market regimes for time series. We utilise the path signature, encoding time series into easy-to-describe objects, and provide a metric structure which establishes a connection between separation of regimes and clustering of points.