Pairs trading on different portfolios based on machine learning


This article presents an advanced visualization and analytics approach for financial research. Statistical arbitrage, particularly pairs trading strategy, has gained ground in the financial market and machine learning techniques are applied to the finance field. The cointegration approach and long short-term memory (LSTM) were utilized to achieve stock pairs identification and price prediction purposes, respectively, in this project. This article focused on the US stock market, investigating the performance of pairs trading on different types of portfolios (aggressive and defensive portfolio) and compare the accuracy of price prediction based on LSTM. It can be briefly concluded that LSTM offers higher prediction precision on aggressive stocks and implementing pairs trading on the defensive portfolio would gain higher profitability during a specific period between 2016 and 2017. However, predicting tools like LSTM only offer limited advice on stock movement and should be cautiously utilized. We conclude that analytics and visualization can be effective for financial analysis, forecasting and investment strategy.

Publication DOI:
Divisions: College of Business and Social Sciences > Aston Business School
College of Business and Social Sciences > Aston Business School > Operations & Information Management
Additional Information: This is the peer reviewed version of the following article: Chang, V, Man, X, Xu, Q, Hsu, C-H. Pairs trading on different portfolios based on machine learning. Expert Systems. 2021; 38:e12649, which has been published in final form at  This article may be used for non-commercial purposes in accordance With Wiley Terms and Conditions for self-archiving. Funding Information: National Natural Science Foundation of China, Grant/Award Number: 61872084; VC Research, Grant/Award Number: VCR 0000052 Funding information
Uncontrolled Keywords: cointegration,long short-term memory,pairs trading,stock price prediction,Control and Systems Engineering,Theoretical Computer Science,Computational Theory and Mathematics,Artificial Intelligence
Publication ISSN: 1468-0394
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
https://onlinel ... 1111/exsy.12649 (Publisher URL)
PURE Output Type: Article
Published Date: 2021-05-01
Published Online Date: 2020-11-18
Accepted Date: 2020-09-30
Authors: Chang, Victor (ORCID Profile 0000-0002-8012-5852)
Man, Xiaowen
Xu, Qianwen
Hsu, Ching Hsien



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record