Graph Clustering for Multi-Pair Statistical Arbitrage in U.S. Equities

Summary

This study proposes a multi-pair statistical arbitrage framework for U.S. equities that uses graph clustering to identify relationships among stocks. It combines quantitative methods with machine-learning classifiers and the Kelly criterion, aiming to improve signal detection, risk management, and resilience to transaction costs. The approach also tests ways to set take-profit and stop-loss rules for daily-frequency trading.

The authors report that all tested approaches beat their corresponding benchmarks under assumed realistic transaction costs, with the strongest technique and parameter combinations producing significantly better performance metrics. They also note sensitivity to changes in some key parameters. The document does not specify the stocks, evaluation period, exact benchmarks, cost assumptions, or sensitivity range, limiting independent assessment and conclusions about performance outside the tested setup.

Key ideas

• Graph clustering is used to organize stocks for a multi-pair statistical arbitrage strategy.
• The framework combines machine-learning classifiers, quantitative methods, and the Kelly criterion.
• Signal detection and risk controls include optimizing daily take-profit and stop-loss rules.
• The authors report benchmark outperformance under assumed realistic transaction costs.
• Reported performance is sensitive to some parameter changes, whose details are not provided.

Tags

# Statistical arbitrage in multi-pair trading strategy based on graph clustering algorithms in US equities market


# Statistical arbitrage in multi-pair trading strategy based on graph clustering algorithms in US equities market









The study seeks to develop an effective strategy based on the novel framework of statistical arbitrage based on graph clustering algorithms. Amalgamation of quantitative and machine learning methods, including the Kelly criterion, and an ensemble of machine learning classifiers have been used to improve risk-adjusted returns and increase immunity to transaction costs over existing approaches. The study seeks to provide an integrated approach to optimal signal detection and risk management. As a part of this approach, innovative ways of optimizing take profit and stop loss functions for daily frequency trading strategies have been proposed and tested. All of the tested approaches outperformed appropriate benchmarks. The best combinations of the techniques and parameters demonstrated significantly better performance metrics than the relevant benchmarks. The results have been obtained under the assumption of realistic transaction costs, but are sensitive to changes in some key parameters.

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.