Proceedings of the 2023 2nd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2023)

<Previous Article In Volume
Next Article In Volume>

Research on Machine Learning Driven Stock Selection Strategy

Authors
Keran Wang1, *
1Faculty of Information Technology, Beijing University of Technology, Beijing, China
*Corresponding author. Email: Keran_Wang@emails.bjut.edu.cn
Corresponding Author
Keran Wang
Available Online 28 August 2023.
DOI
10.2991/978-94-6463-222-4_14How to use a DOI?
Keywords
stock selection; machine learning; anomaly factors; Chinese stock market
Abstract

As a representative technique of artificial intelligence, machine learning could explore the relationship between stock market anomalies and excess returns, and hence develop investment strategies with high performance. This paper provides a comparative analysis of machine learning algorithm applications in the field of quantitative stock selection through detailed and solid empirical evidence. Based on 36 anomalies in the Chinese stock market from January 2011 to March 2022, this paper adopts random forest regression for feature selection and nine machine learning algorithms, including Lasso regression, Ridge regression, Elastic Net regression, SVM, GDBT, XGBoost, LGBM, and neural network, to construct stock return prediction models and portfolios. The empirical results show that the machine learning algorithms can effectively assist in the formulation of quantitative investment strategies in the A-share market, and the long-short portfolio predicted based on the LGBM algorithm can obtain the highest annualized return of 69.33%. This study further examines the importance of the A-share market anomaly factor and finds that the momentum factor and the trading-friction factor have strong predictive power on the excess returns of the A-share market. It also integrates anomaly factors used in academia and industry, and further tests the effectiveness of machine learning algorithms in investment management problems, providing a reference for academic research and practical operation of asset management.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2023 2nd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2023)
Series
Atlantis Highlights in Intelligent Systems
Publication Date
28 August 2023
ISBN
978-94-6463-222-4
ISSN
2589-4919
DOI
10.2991/978-94-6463-222-4_14How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Keran Wang
PY  - 2023
DA  - 2023/08/28
TI  - Research on Machine Learning Driven Stock Selection Strategy
BT  - Proceedings of the 2023 2nd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2023)
PB  - Atlantis Press
SP  - 151
EP  - 159
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-222-4_14
DO  - 10.2991/978-94-6463-222-4_14
ID  - Wang2023
ER  -