Deep Learning Statistical Arbitrage
This work addresses the challenge of exploiting price inefficiencies for arbitrageurs in financial markets, representing a domain-specific advancement with strong empirical gains.
The paper tackles the problem of statistical arbitrage in financial markets by developing a data-driven framework that constructs arbitrage portfolios using conditional latent asset pricing factors and extracts signals with a convolutional transformer to form an optimal trading policy, resulting in consistently high out-of-sample mean returns and Sharpe ratios that substantially outperform benchmarks.
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.