Constructing long-short stock portfolio with a new listwise learn-to-rank algorithm

Abstract

Factor strategies have gained growing popularity in industry with the fast development of machine learning. Usually, multi-factors are fed to an algorithm for some cross-sectional return predictions, which are then further used to construct a long-short portfolio. Instead of predicting the value of the stock return, emerging studies predict a ranked stock list using the mature learn-to-rank technology. In this study, we propose a new listwise learn-to-rank loss function which aims to emphasize both the top and the bottom of a rank list. Our loss function, motivated by the long-short strategy, is endogenously shift-invariant and can be viewed as a direct generalization of ListMLE. Under different transformation functions, our loss can lead to consistency with binary classification loss or permutation level 0-1 loss. A probabilistic explanation for our model is also given as a generalized Plackett-Luce model. Based on a dataset of 68 factors in the China A-share market from 2006 to 2019, our empirical study has demonstrated the strength of our method which achieves an out-of-sample annual return of 38% with Sharpe ratio 2.

Keywords:

• Learn-to-rank
• ListMLE
• Long-short portfolio
• Factor strategy
• Machine learning

JEL Classifications:

• G11
• C45
• C53

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1 Data is obtained from the Wind database, https://www.wind.com.cn/NewSite/data.html

2 For MLP the last ReLU layer is not necessary since there are negative returns.

Additional information

Funding

Wu's research is supported by the Key Laboratory of Mathematical Economics and Quantitative Finance (Ministry of Education) at Peking University.