The Application Of Data Mining And Wavelet Theory In Stock Market

Data mining is derived from business demand, so it has popular value in all kinds of business filed. We will distill the high interest degree data by data mining from large history stock data. Then the data was analyzed, and was forecasted by mathematic tools, and researching the trend of the stock data, which is becoming the focus of stock market.We can further to the research of time-varying self-similar exponent,simulation and forecast wave,stock index,so we can mine effective potential information from raw stock data. These data were used on many field, which include bottle-neck of resolving knowledge explode and getting knowledge, providing exact,timely and full decision-making information.In order to provide theory foundation for stock market analysis, prediction and regulation, the author results thoroughly in stock time series by using data mining and wavelet. The summary as follows:Data distill by k-means analyze technology based on genetic algorithm. The clustering analyze includes: data discrimination is a comparison of the general features of target class data objects with the general features of objects from one or a set of contrasting classes. The methods focus on not only the distance of two objects but also potential describe of class.It cannot make sure the distribution and location of regular periodic change. The author put forward a new detecting method in stock time series, which based on data mining and wavelet theory, and have a research to compare Wavelet Theory with practice, which based on status quo of forecasting technique of stock time series.The innovation of the paper is first to apply data mining and wavelet theory in stock data analysis and forecasting; k-means and genetic algorithm are banded together, which become a effective tool of clustering analysis on data mining. The ARIMA algorithm is applied into forecasting model to become an agility and effective aidant system for decision-making.