Researches Of Stock Intelligent Robot Based On Kaburobo Platform

With the high-speed development of market economy in China, people have stronger consciousness on finance and investment. As a part of market economy, stock market is growing up and standardized. More and more investors are concentrating on stocks. Stock market is an important component in an economic system. The problems of stock market analysis and prediction have been widely studied. Researchers have proposed many theories and technologies about building computer systems to analyze and predict the behavior of a stock market. Data Mining, because of its abilities to deal with indeterministic system with many correlative factors, has been used in many stock market prediction systems.Firstly, this paper analyzes current situation of research on Data Mining, the features of Data Mining and securities analysis. It also points out that Data Mining's application in securities analysis is reasonable and urgent. At the same time, this paper analyzes the features of securities data, and puts forward a mining model which is fit to securities mining.Secondly, this paper presents kaburobo platform, which aims at researching the algorithms of stock auto-trading through the simulation of real stock market, and improves four analytic methods of stock.Finally, the paper researches the application of genetic algorithm in auto-trading, brings the K-MEANS model based on genetic algorithm and shows the results of examinations. K-MEANS and genetic algorithm are banded together, which become an effective tool of clustering analysis on data mining.