Research On The Method Of Forecast The Stock Price Based On Fractal Market

With the rapid development of Chinese stock market, analysis and forecast of stock price are wildly used in domestic investment area. Thanks to increased approach in Chaos and Fractal theory, it shows powerful life force in researching behavior of stock price with rules of nonlinear system. Modeling and forecasting of time series in economics have become a hot spot in nowadays.This thesis mainly discusses the problems in Chinese stock market forecast and focuses on the following aspects.1. Fractal structure of stock market was analyzed and researched. The Chinese stock market of recent years was studied, and the results show that the fluctuation of prices in the stock market has the characteristics of durative, mutation and sensitivity. The fractal structure of Chinese stock market was analyzed based on the fractal R/S analysis theory and combined with the stock market running track.2. The stock price was forecasted. The short-term stock price and stock index were forecasted by the adjustment model of fractal dimension adopted the method of transformation sequences based on the fractal characteristics of the stock market. Four stocks prices were tested and the results show that the relative errors of the true value and the one-step forecast value were less than 0.7% and the relative errors of the true value and the Multi-step forecast value were less than 3.2%.3. The relationship between stock price and turnover was studied. The relationship between stock price and turnover and its impact on the stock price in the future were studied by the method of combined regression analysis with coefficient of elasticity theory. Based on the adjustment model of fractal dimension adopted the method of transformation sequences and Multiple regression forecast turnover. Three samples were used to test, the results show that the forecast data accord with the trend of the stock price in the future.The research results of the thesis provide the base of theory and method for the application of short-term stock price forecast and the stock trend forecast based on fractal market.