Empirical Research About Quantitative Stock Picking Based on Machine Learning

DOI

10.2991/aebmr.k.191217.026How to use a DOI?

Keywords

Machine learning, Random Forest, XGBoost, Multifactor stock selection

Abstract

This study mainly uses artificial intelligence and machine learning technology to build stock selection models to help investors choose stocks reasonably. In this paper, six machine learning models were constructed for comparison and backtesting based on the framework of the machine learning stock selection. By comparing the model classification accuracy, AUC, and other index, XGBoost and Random Forest were selected, and the portfolio was constructed. According to the analysis, the portfolio could obtain an above-average rate of return, and the portfolio obtained a net value of about 1.5 times that of the benchmark portfolio during the two-year investment test period.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zheng Zhongbin
AU  - Fang Jinwu
PY  - 2019
DA  - 2019/12/20
TI  - Empirical Research About Quantitative Stock Picking Based on Machine Learning
BT  - Proceedings of the 2019 International Conference on Economic Management and Cultural Industry (ICEMCI 2019)
PB  - Atlantis Press
SP  - 138
EP  - 141
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.191217.026
DO  - 10.2991/aebmr.k.191217.026
ID  - Zhongbin2019
ER  -