Analysis And Forecast Of Financial Market Returns Based On Symbolic Time Series Analysis

The analysis and forcast of financial market returns can not only provide the basis for investors to make investment decisions, but provide the basis for government to formulate various macro policies. The study on financial market returns volatility is the base of financial risk analysis, capital asset pricing research and so on. So in order to make the quantitative analysis of the financial markets effective, we must accurately describe the volatility characteristics of financial markets earnings. Financial market is essentially a nonlinear system. Chaos, split-ended and fractal all are the nonlinear essential characteristics of financial markets. Unlike traditional methods, the symbolic time series analysis method can reflect the characteristics of returns in the angle of big scale, so it is suitable for the analysis of nonlinear dynamic system. The main work of the dissertation includes:1. This paper reviews the background, significance and status about financial market returns study, then put forward the innovation of this paper.2. In this paper, the symbolic time series analysis method is described in detail, including the calculation of relevant statistics.3. Symbolic time series analysis method is introduced into the study of financial markets. The analysis and forecasting method of assets returns based on symbolic time series analysis is proposed. Unlike traditional methods, the method proposed can reflect the characteristics of returns in the angle of big scale and realize the forecasting of returns levels. The effectiveness and feasibility of the method are proved by the analysis of the return series of six indexes which are Shanghai composite stock, Shenzhen component stock, Shanghai industrial stock, Shanghai commercial stock, Shanghai property stock and Shanghai utility stock.4. This paper analyzes the daily return characteristics and differences of the Shanghai stock exchange's comprehensive index, industrials index, commercial index, real estate index and utilities index by the method of symbolic time series analysis. What is more, the difference between the daily return series of Shanghai composite index and Shenzhen component index before and after June 1 2008 is also analyzed by the method proposed. 5. This paper introduces the method of symbolic time series analysis into the analysis of structure change, studies the structural changes of complex system's running mode by the technology of sliding windows and proposes a new non-parametric method to reflect the Structural changes of complex system. The feasibility of the method is checked by the analysis of the historical index of Shanghai composite stock.Finally, summary of the full text content is made. The advantages, disadvantages and application prospects are also analyzed.This paper is a part of the project Study on Financial Volatility Based on Symbolic Time Series Analysis (item number: 70971097), which is supported by national natural science foundation.