Pairs Trading via Unsupervised Learning

41 Pages Posted: 4 May 2021 Last revised: 7 Jun 2021

See all articles by Chulwoo Han

Chulwoo Han

Sungkyunkwan University

Zhaodong He

Durham University

Alenson Jun Wei Toh

Nanyang Technological University

Date Written: April 28, 2021


This paper develops a pairs trading strategy via unsupervised learning. Unlike conventional pairs trading strategies that identify pairs based on return time series, we identify pairs by incorporating firm characteristics as well as price information. Firm characteristics are revealed to provide important information for pair identification and significantly improve the performance of the pairs trading strategy. Applied to the US stock market from January 1980 to December 2020, the long-short portfolio constructed via the agglomerative clustering earns a statistically significant annualized mean return of 24.8% and a Sharpe ratio of 2.69. The strategy remains profitable after accounting for transaction costs and removing stocks below 20% NYSE-size quantile. A host of robustness tests confirm that the results are not driven by data snooping.

Keywords: Unsupervised learning, Pairs trading, K-means clustering, DBSCAN, Agglomerative clustering

JEL Classification: G11, G12

Suggested Citation

Han, Chulwoo and He, Zhaodong and Toh, Alenson Jun Wei, Pairs Trading via Unsupervised Learning (April 28, 2021). Available at SSRN: or

Chulwoo Han

Sungkyunkwan University ( email )

25-2, Sungkyunkwan-ro
Seoul, 03063

Zhaodong He (Contact Author)

Durham University ( email )

Mill Hill Lane
Durham, Durham DH1 3HP
United Kingdom

Alenson Jun Wei Toh

Nanyang Technological University ( email )

50 Nanyang Avenue
Singapore, Singapore 799377

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics