Deep Learning Statistical Arbitrage

68 Pages Posted: 8 Jun 2021 Last revised: 7 Oct 2022

See all articles by Jorge Guijarro-Ordonez

Jorge Guijarro-Ordonez

Stanford University - Department of Mathematics

Markus Pelger

Stanford University - Department of Management Science & Engineering

Greg Zanotti

Stanford University, School of Engineering, Management Science & Engineering

Date Written: March 15, 2019

Abstract

Statistical arbitrage exploits temporal price differences between similar assets. We develop a unifying conceptual framework for statistical arbitrage and a novel data driven solution. First, we construct arbitrage portfolios of similar assets as residual portfolios from conditional latent asset pricing factors. Second, we extract their time series signals with a powerful machine-learning time-series solution, a convolutional transformer. Lastly, we use these signals to form an optimal trading policy, that maximizes risk-adjusted returns under constraints. Our comprehensive empirical study on daily US equities shows a high compensation for arbitrageurs to enforce the law of one price. Our arbitrage strategies obtain consistently high out-of-sample mean returns and Sharpe ratios, and substantially outperform all benchmark approaches.

Keywords: statistical arbitrage, pairs trading, machine learning, deep learning, big data, stock returns, convolutional neural network, transformer, attention, factor model, market efficiency, investment

JEL Classification: C14, C38, C55, G12

Suggested Citation

Guijarro-Ordonez, Jorge and Pelger, Markus and Zanotti, Greg, Deep Learning Statistical Arbitrage (March 15, 2019). Available at SSRN: https://ssrn.com/abstract=3862004 or http://dx.doi.org/10.2139/ssrn.3862004

Jorge Guijarro-Ordonez

Stanford University - Department of Mathematics ( email )

450 Jane Stanford Way
Stanford, CA 94305
United States

Markus Pelger (Contact Author)

Stanford University - Department of Management Science & Engineering ( email )

473 Via Ortega
Stanford, CA 94305-9025
United States

Greg Zanotti

Stanford University, School of Engineering, Management Science & Engineering ( email )

473 Via Ortega
Stanford, CA 94305-9025
United States

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

Paper statistics

Downloads
3,190
Abstract Views
7,863
Rank
5,841
PlumX Metrics