Stock Investment Risk Measuring And Stock Trend Forecasting Based On Genetic Neural Network

With the economic growth and the conversion of people's investment consciousness, the stock has become an important part of people's economy life in modern time. Accordingly the proceeds of stock investment always equal the risk, so investors keep finding its internal disciplinarian and looking for effective analytic methods and tools. Then, because of the complexity of inside structure of stock market and levity of exterior factors, these make stock market prediction a complex problem, the traditional prediction tools have not met its needs.In this paper the theory of CAPM is taken as reference and on the basic of generally describing the main ideas of CAPM, the outline of CAPM is outlining and methods of stock risk analyzing and prediction modeling are presented to study the risk behavior of stock. Meantime, on the basic of deeply analyzing problems of stock market prediction and comparing every kind of stock price prediction methods, the method of adopting genetic neural network to analyze stock market and build prediction model.As examples of applications, in this paper representative stocks of Shanghai A-Share Market have been applied to stock risk prediction model and the results of prediction show that whole trend of stock market produces an effect on this model's application. Meantime, representative Shanghai A-Share index and stocks have been applied to train the established stock trend prediction model, the stock prices have been predicted by using the trained network and the results of prediction show that relative errors of stock prediction prices and actual stock prices are inside a smaller error margin.