Attention Factors for Cost-Aware Statistical Arbitrage

Summary

The paper develops a framework that learns conditional latent factors to identify related equities, detect relative mispricing, and form a trading policy that accounts for trading costs. Its attention factors are built from embeddings of firm characteristics, allowing interactions among those characteristics. A sequence model extracts time-series signals from residual portfolios, and factor estimation is jointly optimized with the arbitrage strategy to target risk-adjusted profitability after costs.

The authors report an out-of-sample Sharpe ratio above four for the largest U.S. equities over a 24-year period, and a one-step solution with a Sharpe ratio of 2.3 net of transaction costs. They also argue that weaker factors can still matter for arbitrage decisions. The excerpt does not specify portfolio construction, execution assumptions, or robustness tests, so the reported results should be understood within the study's stated universe and evaluation design.

Key ideas

• Conditional latent attention factors are learned from firm-characteristic embeddings.
• Residual factor portfolios provide time-series signals through a sequence model.
• Factor learning and strategy construction are optimized jointly to account for trading costs.
• The study reports strong out-of-sample Sharpe results for large U.S. equities and emphasizes the value of weak factors.

Tags

# Attention Factors for Statistical Arbitrage


# Attention Factors for Statistical Arbitrage









Statistical arbitrage exploits temporal price differences between similar assets. We develop a framework to jointly identify similar assets through factors, identify mispricing and form a trading policy that maximizes risk-adjusted performance after trading costs. Our Attention Factors are conditional latent factors that are the most useful for arbitrage trading. They are learned from firm characteristic embeddings that allow for complex interactions. We identify time-series signals from the residual portfolios of our factors with a general sequence model. Estimating factors and the arbitrage trading strategy jointly is crucial to maximize profitability after trading costs. In a comprehensive empirical study we show that our Attention Factor model achieves an out-of-sample Sharpe ratio above 4 on the largest U.S. equities over a 24-year period. Our one-step solution yields an unprecedented Sharpe ratio of 2.3 net of transaction costs. We show that weak factors are important for arbitrage trading.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.