Randomized Signature Methods in Optimal Portfolio Selection

TL;DR

This paper demonstrates the effectiveness of Randomized Signature Methods in estimating non-linear drifts for multi-variate financial markets, improving portfolio optimization despite the challenges of low signal-to-noise ratios.

Contribution

It provides empirical evidence that Randomized Signatures enable high-dimensional, scalable feature extraction for portfolio selection in real-world financial data.

Findings

Effective drift estimation in multi-variate markets

Improved portfolio optimization with Randomized Signatures

Robustness to transaction costs

Abstract

We present convincing empirical results on the application of Randomized Signature Methods for non-linear, non-parametric drift estimation for a multi-variate financial market. Even though drift estimation is notoriously ill defined due to small signal to noise ratio, one can still try to learn optimal non-linear maps from data to future returns for the purposes of portfolio optimization. Randomized Signatures, in contrast to classical signatures, allow for high dimensional market dimension and provide features on the same scale. We do not contribute to the theory of Randomized Signatures here, but rather present our empirical findings on portfolio selection in real world settings including real market data and transaction costs.