A hybrid convolutional neural network with long short-term memory for statistical arbitrage. Issue 4 (3rd April 2023)

• Record Type: Journal Article
• Authors: Eggebrecht, P.; Lütkebohmert, E.
• Is Part Of: Quantitative finance. Volume 23:Issue 4(2023)
• Page Start: 595
• Page End: 613
• Publication Date: 2023-04-03
• Subjects: Statistical arbitrage -- Pairs trading -- Deep learning -- Convolutional neural network -- Long short-term memory; C32 -- C38 -- C41 -- C45 -- G11; Finance -- Periodicals; Business mathematics -- Periodicals; Finance -- Mathematical models -- Periodicals; Investments -- Mathematics -- Periodicals; Economics -- Periodicals; Finances -- Modèles mathématiques -- Périodiques; 332.015118
• DOI: 10.1080/14697688.2023.2181707
• Languages: English
• ISSNs: 1469-7688

Abstract

Abstract : We propose a CNN-LSTM deep learning model, which has been trained to classify profitable from unprofitable spread sequences of cointegrated stocks, for a large scale market backtest ranging from January 1991 to December 2017. We show that the proposed model can achieve high levels of accuracy and successfully derives features from the market data. We formalize and implement a trading strategy based on the model output which generates significant risk-adjusted excess returns that are orthogonal to market risks. The generated out-of-sample Sharpe ratio and alpha coefficient significantly outperform the reference model, which is based on a standard deviation rule, even after accounting for transaction costs.