Stock Prediction Based On Genetic-BP Neural Network

With the economic growth and the conversion of people's investment consciousness, stock has become an important part of people's life in modern time. Investment in stock has great become one of focouses of public topic. How to keep the development and boost stock market is becoming the emphasis of concern and research of manager and investor. The proceeds of stock investment always equal the risk. That means the good proceeds is based on the high risk of failure. Therefore, the study of stock prediction method has great application value and theoretical significance. The complexity of inside structure and levity of exterior complication in system of stock market make stock market predication a complex problem. The traditional methods and tools have not met its challenge, the thesis presents a method of modeling stock market using neural network that is based on thorough study of stock investment theories and stock prediction methods.Through in-depth analysis of investment theory of stock market and forecasting methods of stock price, the thesis presents a method of the prediction model of stock market based on BP neural network. Stock market is a very complex nonlinear dynamic system, then neural network has the capability of approximating any nonlinear system and speciality of self-learning and self-adapting. The experiments prove that the method of modeling stock market using neural network has a satisfying result in near-period stock prediction. The trend of stock market looks like disorderly, but it has internal disciplinarian actually, which is the base of stock prediction using neural network. BP neural network find out the disciplinarian of stock market through study of historical datum and store them in the weights and valve values of the neural network for forecasting the trend in the future.The paper presents genetic-BP algorithm for the high-nonlinear speciality of stock market and the shortcomings of basic BP algorithms including the slow convergence speed and local extremun. The thesis analyses the theory of stock market prediction, based on BP neural network and the prediction model of stock market, which has been established using three-layer feed-forward neural network. Problems including the structure of network, number of hidden nodes, the choose & pretreatment of swatch datum and the determination of preliminary parameters, which have been discussed. The genetic-BP algorithm carries through whole-space search using genetic algorithm. The genetic algorithm pays attention to unknown-area search, it has high speed, relative low precision, will not get into local extremun.The BP algorithm searches the area including whole-space minimum. It can improve speed and precision. Theoretical analysis and experiment result show that the method of stock prediction using neural network is feasible and efficient. It proves that genetic-BP algorithm can improve the speed and credibility, which has favorable foreground.Through lots experiment on stock prediction, this paper investigates the influence on the stock prediction results, which is exerted by the change of parameter. It presents some advices on how to improve the performance of neural network.