Deep Learning Statistical Arbitrage

TL;DR

This paper introduces a new data-driven approach to statistical arbitrage using convolutional transformers to generate trading signals, resulting in high returns and Sharpe ratios in US equities.

Contribution

It presents a unifying framework combining residual portfolios from latent asset pricing factors with a convolutional transformer for signal extraction and an optimal trading policy.

Findings

High out-of-sample mean returns and Sharpe ratios

Substantially outperforms benchmark approaches

Empirical validation on US equities data

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.