Randomized Signature Methods in Optimal Portfolio Selection

38 Pages Posted: 17 Jan 2024

See all articles by Erdinc Akyildirim

Erdinc Akyildirim

University of Bradford

Matteo Gambara

INAIT SA

Josef Teichmann

ETH Zurich; Swiss Finance Institute

Syang Zhou

ETH

Date Written: December 26, 2023

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 constrast 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.

Keywords: Machine Learning, Randomized Signature, Drift estimation, Returns forecast, Portfolio Optimization, Path-dependent Signal

JEL Classification: C21, C22, G11, G14, G17

Suggested Citation

Akyildirim, Erdinc and Gambara, Matteo and Teichmann, Josef and Zhou, Syang, Randomized Signature Methods in Optimal Portfolio Selection (December 26, 2023). Available at SSRN: https://ssrn.com/abstract=4676478 or http://dx.doi.org/10.2139/ssrn.4676478

Erdinc Akyildirim

University of Bradford ( email )

Bradford
Bradford, BD9 4JL
United Kingdom

Matteo Gambara (Contact Author)

INAIT SA ( email )

Av. du Tribunal-Fédéral 34
Lausanne, 1005
Switzerland

Josef Teichmann

ETH Zurich ( email )

Rämistrasse 101
ZUE F7
Zürich, 8092
Switzerland

HOME PAGE: http://www.math.ethz.ch/~jteichma

Swiss Finance Institute ( email )

c/o University of Geneva
40 Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

Syang Zhou

ETH ( email )

Zurichbergstrasse 18
Zürich, 8032
Switzerland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
277
Abstract Views
586
Rank
212,201
PlumX Metrics