Font Size: a A A

The Study Of Forecasting And Application For Stock Market Based On Wavelet Analysis And Neural Networks

Posted on:2007-06-25Degree:MasterType:Thesis
Country:ChinaCandidate:L PanFull Text:PDF
GTID:2189360212966520Subject:Applied Mathematics
Abstract/Summary:PDF Full Text Request
Stock market is a hotspot that investors, administrators and economists pay attention to. Many forecasting model academicians focused on the research of stock since 19B.C. since the stock market was established. With the development of the stock investing in China, its influence become more and more great, and it is acutely required to deeply understand its movement law. In recently years, many academicians have regarded stock market as a nonlinear deterministic kinetic system Using the rules of nonlinear deterministic system to study the stock price shows more and more vitality. Along with the development of nonlinear theory and artificial intelligence, wavelet analysis and wavelet network become cogent tools for financial market analysis and forecasting.This paper does deeply research on the wavelet network and establishes a short term prediction model which serves the time series analysis of stock price.The main research is the application and realization of the wavelet network prediction. The main work is as the following:First of all, in the text the essentiality and feasibility are analyzed in the mass reflecting the fact in the home and aboard. Base on it, the theory and method of system modeling is used to strengthen the restriction step by step, the abstract and complicated finance system will be translated into a comparatively clear black-box system which can be simulated and approached. At the same time, the brief-time validity will be accepted by nature in this course.Secondly, in this paper, the theory and method of neural network and wavelet are studied and understood especially in their merit and defect, a wavelet neural network is advanced which may be more suit to the stock-indices series prediction by reference and use reference all kinds of current theory and method on wavelet, and deriving their merit.At last, in order to validate the correctness of the theory and method, the programmer is made with the software of MATLAB, and it is used to predict 30 dates in 2006. The basic theory and method discussed in this paper makes use of wavelet neural network for the prediction in time series of stock indices. Moreover, the data of shanghai Exchange between 2005 and 2006. and the result is satisfactory, its precision is excel to artificial neural network.
Keywords/Search Tags:neural networks, wavelet transform, wavelet neural network, wavelet analysis, system modeling, stock indices, time series, the prediction of stock indices
PDF Full Text Request
Related items