Multi-factor Data Mining Analysis of Stock Index Volatility

Abstract

In the study of the relationship between macroeconomy and stock price volatility, the traditional method is to unify the mixed data by summation or interpolation before modelling. The biggest disadvantage of this method is that it leads to inflated information and affects the validity of the model. In this paper, we use GARCH-MIDAS model and make full use of high-frequency data to study the impact of consumer price index and industrial production growth rate on the long-run and short-run components of stock price volatility. In the empirical study, Shanghai Securities Composite Index and the Shanghai-Shenzhen 300 Index are selected as the research objects, and based on January 2010 to February 2021 daily rate of return data for analysis, and the results show that the model can describe the relationship between macroeconomy and stock market volatility. The consumer price index and industrial production growth rate have a positive impact on long-run stock volatility.