A hybrid convolutional neural network with long short-term memory for statistical arbitrage
Authors:
- 9 March 2023
- journal article
- research article
- Published by Taylor & Francis in Quantitative Finance
- Vol. 23 (4) , 595-613
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.Keywords
This publication has 45 references indexed in Scilit:
- Pairs trading and outranking: The multi-step-ahead forecasting caseEuropean Journal of Operational Research, 2010
- Statistical arbitrage in the US equities marketQuantitative Finance, 2010
- Pairs Trading: Performance of a Relative-Value Arbitrage RuleThe Review of Financial Studies, 2006
- The use of data mining and neural networks for forecasting stock market returnsExpert Systems with Applications, 2005
- Learning to Forget: Continual Prediction with LSTMNeural Computation, 2000
- OPTICSACM SIGMOD Record, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Multifactor Explanations of Asset Pricing AnomaliesThe Journal of Finance, 1996
- Testing for unit roots in autoregressive-moving average models of unknown orderBiometrika, 1984