Building Cross-Sectional Systematic Strategies By Learning to Rank

The Journal of Financial Data Science Spring 2021, jfds.2021.1.060; DOI: https://doi.org/10.3905/jfds.2021.1.060

12 Pages Posted: 19 Feb 2021 Last revised: 23 Aug 2022

See all articles by Daniel Poh

Daniel Poh

University of Oxford - Oxford-Man Institute of Quantitative Finance

Bryan Lim

University of Oxford - Oxford-Man Institute of Quantitative Finance

Stefan Zohren

University of Oxford - Oxford-Man Institute of Quantitative Finance

Stephen Roberts

University of Oxford - Oxford-Man Institute of Quantitative Finance

Date Written: December 12, 2020

Abstract

The success of a cross-sectional systematic strategy depends critically on accurately ranking assets prior to portfolio construction. Contemporary techniques perform this ranking step either with simple heuristics or by sorting outputs from standard regression or classification models, which have been demonstrated to be sub-optimal for ranking in other domains (e.g. information retrieval). To address this deficiency, we propose a framework to enhance cross-sectional portfolios by incorporating learning-to-rank algorithms, which lead to improvements of ranking accuracy by learning pairwise and listwise structures across instruments. Using cross-sectional momentum as a demonstrative case study, we show that the use of modern machine learning ranking algorithms can substantially improve the trading performance of cross-sectional strategies -- providing approximately threefold boosting of Sharpe Ratios compared to traditional approaches.

Keywords: Momentum Strategies, Systematic Trading, Portfolio Construction, Machine Learning, Learning to Rank, Information Retrieval, Deep Neural Networks

Suggested Citation

Poh, Daniel and Lim, Bryan and Zohren, Stefan and Roberts, Stephen, Building Cross-Sectional Systematic Strategies By Learning to Rank (December 12, 2020). The Journal of Financial Data Science Spring 2021, jfds.2021.1.060; DOI: https://doi.org/10.3905/jfds.2021.1.060 , Available at SSRN: https://ssrn.com/abstract=3751012 or http://dx.doi.org/10.2139/ssrn.3751012

Daniel Poh (Contact Author)

University of Oxford - Oxford-Man Institute of Quantitative Finance ( email )

Eagle House
Walton Well Road
Oxford, Oxfordshire OX2 6ED
United Kingdom

Bryan Lim

University of Oxford - Oxford-Man Institute of Quantitative Finance ( email )

Eagle House
Walton Well Road
Oxford, Oxfordshire OX2 6ED
United Kingdom

Stefan Zohren

University of Oxford - Oxford-Man Institute of Quantitative Finance ( email )

Eagle House
Walton Well Road
Oxford, Oxfordshire OX2 6ED
United Kingdom

Stephen Roberts

University of Oxford - Oxford-Man Institute of Quantitative Finance ( email )

Eagle House
Walton Well Road
Oxford, Oxfordshire OX2 6ED
United Kingdom

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

Paper statistics

Downloads
1,182
Abstract Views
2,478
rank
25,698
PlumX Metrics