• ISSN: 2010-023X (Print)
    • Abbreviated Title: Int. J. Trade, Economics and Financ.
    • Frequency: Quaterly
    • DOI: 10.18178/IJTEF
    • Editor-in-Chief: Prof.Tung-Zong (Donald) Chang
    • Managing Editor: Ms. Shira. W. Lu
    • Abstracting/ Indexing:  Crossref, Electronic Journals Library , EBSCO
    • E-mail: ijtef.editorial.office@gmail.com
IJTEF 2023 Vol.14(3): 49-55 ISSN: 2010-023X
DOI: 10.18178/ijtef.2023.14.3.755

An Attention Based Multi-gate Mixture-of-Experts Model for Quantitative Stock Selection

Keyao Li* and Jungang Xu

Abstract—As a kind of typical quantitative trading strategy, quantitative stock selection has attracted increasing attention of investors in recent years, and the application of many traditional economic models and machine learning models to the stock selection has yielded quite valuable results. However, most of the existing research are still limited to the learning of a single target, which does not serve the needs of multiple investment objectives well. To address these issues, we propose an Attention based Multi-gate Mixture-of-Experts (AMMOE), which is a multi-tasking model obtained by combining the MMOE and attention modules. We apply this model to extract information from stock characteristics using correlations among stock indicators to predict different stock indicators simultaneously, improve the predictive performance of each target, and provide a valuable reference for portfolio construction. The experimental results show that all portfolios with the AMMOE model achieve the highest returns and significant advantage in most backtesting metrics compared to other machine learning models.

Index Terms—Multi-task learning, quantitative stock selection, portfolio construction, backtesting

K. Li and J. Xu are with the School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China.

[PDF]

Cite: Keyao Li and Jungang Xu, "An Attention Based Multi-gate Mixture-of-Experts Model for Quantitative Stock Selection," International Journal of Trade, Economics and Finance vol.14, no.3, pp. 49-55, 2023.

Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Copyright © 2008-2024. International Journal of Trade, Economics and Finance. All rights reserved.
E-mail: ijtef.editorial.office@gmail.com