Establishment and Analysis of Multi-Factor Stock Selection Model Based on Support Vector Machine in CSI 300 Index Constituent Stocks Market

Abstract

This paper uses the SVM (support vector machine) method to model the multi-factor stock selection and conducts research in Chinese Stock Market. The CSI 300 Index accounts for about 60% of the market value of Chinese Stock Market, we uses the principal component analysis for dimensionality reduction, reducing the number of original factors to 13, and the cumulative contribution rate reached 78.5372%, which reduced the complexity of SVM classification. In terms of model building, since the linear SVM method cannot be reasonably classified, this paper uses the radial basic kernel function and then classifies them, and obtains a stock selection model with strong effectiveness, which can beat the benchmark in all test sets. In terms of stock selection, we sort the stocks according to the sample values generated by the prediction of the model, and the reliability of the result obtained was high, which is the innovation of this paper.

A Multi-Criteria Based Stock Selection Framework in Emerging Market

“…The study established an effective investment decision model and also provides a reference basis for stock-picking. Dou et al (2021) used Support Vector Model (SVM) for multi-factor stock selection. The study uses quarterly financial information such as profitability, income quality, debt-paying ability, etc of all the constituent stocks of the CSI 300 Index from 2013 to 2017 along with the risk indicators and investor sentiment indicators to make the model more comprehensive and effective.…”