Multifactor Stock Selection Strategy Based on Machine Learning: Evidence from China

Jieying Gao,Huan Guo,Xin Xu,Sameh S Askar

doi:10.1155/2022/7447229

Jieying Gao, Huan Guo + Show 2 more

Open Access

https://doi.org/10.1155/2022/7447229

Copy DOI

Journal: Complexity	Publication Date: Feb 3, 2022
Citations: 3	License type: CC BY 4.0

Affiliation: Capital University of Economics and Business

Abstract

Machine learning methods have been used in multifactor stock strategy for years. This paper uses three machine learning methods and linear regression method to find the most appropriate approach. First, a framework is established and 10 style factors and 30 industry factors are chosen. Second, four methods are used to forecast portfolio returns and compared by predicting returns, successful rate, and Sharpe ratio. Finally, this paper draws conclusion. The main findings are as follows: the support vector regression has the most stable successful rate for predicting, while ridge regression and linear regression have the most unstable successful rate with more extreme cases; algorithm of support vector regression fitting higher-degree polynomials in Chinese A-share market is optimized, compared with the traditional linear regression both in terms of stock return and retracement control; the results of support vector regression significantly outperforming the CSI 500 index prove further.

Highlights

Quantitative trading in securities market usually adopts CTA strategy, intraday highfrequency strategy, and multifactor quantitative strategy.e multifactor models are widely used in the stock market, including Fama–French three-factor asset pricing model [1], Carhart four-factor model [2], and the further improved five-factor and six-factor models
Based on the Chinese stock market, this study aims to establish a forecasting framework to predict the relationship between abnormal factors and excess returns with different methods, conducting a systematic test and evaluating which method is best. erefore, this study puts forward three research questions: (1) Is the machine learning model superior to the traditional predictive model? To verify the first observation, a traditional linear regression model and three machine learning algorithm models are selected in this study
Mean square error (MSE) is the sum of squares of the difference between the true value and the predicted value of the test set divided by the number of samples in the test set

Summary

Introduction

Quantitative trading in securities market usually adopts CTA (commodities trading adviser) strategy, intraday highfrequency strategy, and multifactor quantitative strategy.e multifactor models are widely used in the stock market, including Fama–French three-factor asset pricing model [1], Carhart four-factor model [2], and the further improved five-factor and six-factor models. E traditional factor strategies are usually used to forecast stock returns by scoring factor exposures, and linear regression methods commonly used are time series regression, crosssectional regression, Fama and MacBeth [3] regression, and Hansen GMM regression [4]. One of the reasons for the disappearance of excess returns is the increasing convergence of prediction and trading models using traditional methods in the security market, which leads to failure. Major financial institutions have adopted new technologies and methods to improve quantitative trading strategies in security market transactions

Objectives

Results

Conclusion