Attention Factors for Statistical Arbitrage

2025-10-13

AI Summary

This paper addresses the joint problem of identifying similar assets, detecting mispricing opportunities, and constructing trading strategies to maximize risk-adjusted returns net of transaction costs. To this end, we propose the “Attention Factor”—a conditional latent factor framework that models complex cross-asset interactions via learnable firm-level feature embeddings, and jointly optimizes factor extraction and trading decisions in an end-to-end manner. Our method unifies feature embedding, residual portfolio signal extraction, and a generic sequence model within a single statistical arbitrage learning architecture. Evaluated on out-of-sample U.S. equities in 2024, the strategy achieves a Sharpe ratio of 4.0 pre-transaction costs and 2.3 post-costs—demonstrating both the viability of weak signals in high-frequency statistical arbitrage and the practical robustness of the proposed framework.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Statistical Relational/Logic Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

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.

Problem

• Identifying similar assets and mispricing for arbitrage
• Developing a joint framework for factor learning and trading
• Maximizing risk-adjusted returns after accounting for transaction costs

Innovation

• Attention Factors learn conditional latent factors for arbitrage
• Jointly estimate factors and trading strategy to maximize profitability
• Use sequence models on residual portfolios for time-series signals