The Symbolic Time Series Analysis Of Financial Volatility Based On The Realized Volatility

Financial volatility is the barometer of risk in financial markets. Facing immaturefinancial markets in our country, the ups and downs of financial volatility illustrate thestability of the domestic financial market. In order to enhance investors’ risk awarenessand guide them to invest rationally to promote the development of the financial marketsorderly and healthily, it is necessary to analyze the financial risk by studying financialvolatility. Therefore, it is importantly theoretical and practical to forecast and analyzesomething with financial volatility for our financial markets. Financial markets whichvary timely is a complex, changeable and nonlinear systems. It is influenced by manyfactors. Based on the above considerations, it can simulate the complex and changeablefinancial markets better to analyze financial volatility with symbolic time series whichcan provide an important basis for domestic and foreign scholars and promote domesticand foreign to develop healthily. Therefore, this thesis forecast the financial volatility toguide the behavior of investors by Grey-Markov model and classify financial risk bycluster analysis to help the investors achieve risk aversion and risk hedging.Firstly, this thesis introduces the research background of financial volatility, proposepractical significance of studying financial volatility and then sum up the research resultsof financial volatility, realized volatility and symbolic time series analysis, which indicatethe innovation, purpose and significance of it. Secondly, this thesis presents the somespecific methods, such as Grey-Markov model, realized volatility and symbolic timeseries analysis, cluster analysis and so on. What’s more, focusing on Grey-Markov modeland cluster analysis theoretical framework and work steps provides a theoretical basis forrelated research of this thesis. Finally, this thesis forecast the financial volatility based onthe realized volatility time series of the Shanghai Composite Index and ShenzhenComponent Index in China’s domestic financial markets by Grey-Markov model. Inaddition, it classify the financial volatility time series by cluster analysis to make enableinvestors to understand the domestic financial markets comprehensively and investrationally under their risk preferences.This thesis is one part of the Financial volatility research based on symbolic timeseries analysis which is Natural Science Foundation project.