Deep Learning Statistical Arbitrage
Abstract
Statistical arbitrage exploits temporal price differences between similar assets. We develop a comprehensive 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, which maximizes risk-adjusted returns under constraints. Our comprehensive empirical study on daily U.S. equities shows a high compensation for arbitrageurs to enforce the law of one price. Our arbitrage strategies obtain considerable out-of-sample mean returns and Sharpe ratios, and outperform all benchmark approaches.
This paper was accepted by Agostino Capponi, finance.
Funding: The authors thank MSCI for generous research support.
