This paper mainly studies the specific mechanism of investor sentiment affecting stock market volatility. With the help of Pollet and Wilson\'s theory of volatility decomposition, it performs a comparative analysis based on big data strategy and sources. This paper collects the data of web news emotion index, web search volume, social network emotion index, social network heat index, and establishes corresponding analysis index. After correlation analysis and Granger causality tests, it extracts the indicators which have significant correlation with the financial market and brings them into forecasting analysis. The model constructs market volatility index and analyzes the correlation between investor sentiment and stock price changes. In empirical study, the deviation between stock price and value is introduced as an explanatory variable, and the logarithmic return of stock is used to measure the volatility of stock price. It is found that the stock market volatility index compounded by the stock market sentiment index has a strong predictive ability for the stock market volatility turning point in the larger turbulent situation, especially for the one to two day decline turning point ahead of schedule, and it has a strong practical role for the stock market volatility prediction, as well as for financial market risk aversion.
Feature Extraction
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask,hadoop Frontend :-python Backend:- MYSQL
₹10000 (INR)
2019