Volatility Analysis of Chinese Stock Market Using High-Frequency Financial Big Data

With the recent development of computer technology, the high frequency financial big data have been generated timely and more conveniently. However, the particularity of high-frequency big data has raised a number of major challenges for data analysis. The existing mathematical models that were designed for analyzing daily financial data may no longer be suitable for studying high-frequency big data. To tackle this challenge, this work explores the appropriate model that is able to analyze the high-frequency financial Big Data from the Shanghai composite index. For analyzing market volatility,we conduct three comparison studies for different mathematical models. We first compare the effect of two types GARCH (generalized autoregressive conditional heteroskedasticity)models. Numerical results suggest that the volatility proxy model has a better effect than the model based on the return ofShanghai composite index. This study leads to the comparisonstudy of the GARCH(1,1) model and GJR(1,1) (Glosten-Jagannathan-Runkle) model. The result show that the GJR(1,1) model is more efficient than the GARCH(1,1) model. Finally weintroduce the ARMA model based on the GJR volatility proxy model. Analysis results indicate that the ARMA(2,1)-GJR volatility proxy model is the most effective one to study market volatility. The volatility persistence parameter is 0.952, which is very close to 1. In addition, the p-value of the Ljung-Box test is 0.729, which suggests that this model can not only correct the problem of residual but also reflect the leverage effect and long memory character of the Chinese stock market.