With the continuous development of national economy,the stock investment becomes more and more people choose.In order to circumvent the risk of stock investment and maximum income on investment,stock price forecasting becomes the most concern of the investors.In order to guarantee stable income and reduce the investment risk,study a higher accuracy of stock price prediction model has became a very important practical significance.Due to the uncertainty of the primary and secondary relations,the stock price is not only influenced by traders and policy but also the subjective consciousness,so the price of a stock is a kind of strong randomness of data.The traditional prediction method is difficult to accurately predict the stock price.This paper adopts the method of BP neural network combined with genetic algorithm for stock price prediction research.Because of random initial weights of BP neural network and genetic algorithm is easy to fall into local optimal solution;this paper presented a prediction model based on adaptive genetic algorithm to optimize the BP neural network,Using adaptive genetic algorithm to optimize the initial weights of BP neural network,through the analysis of the BP neural network to forecast the stock price.Because of stock price volatility,the single BP neural network is unable to obtain a higher prediction,this paper also gives a kind of neural network based on the combination of adaptive genetic algorithm to optimize price forecast model,to improve the accuracy.Finally this paper simulated the stock price prediction model by MATLAB,and use the real stock data shows that prediction model has higher prediction accuracy. |