The Application Of Artificial Neural Network Stock Prediction And Research

Stock market is closely related with the economic activities. It is not only the weatherglass of Macro-economy, but also an important index to analyze Micro-economy. Within recent ten years, stock has penetrated into our daily life and the population of investing stock has increased to millions. For the enormous profits, study on the internal rule of stock has been a hot topic and there emerge a lot of theories and methods to predict the trend of stock market. To some degree, these stock market prediction methods have revealed the running rule of stock market. However, due to the complexity of the internal structure of the stock price system and the changeability of the external factors, the effect of present prediction methods is not satisfactory.The fluctuation of stock price is a dialectical consolidation of randomness and regularity. In short term and local view, it shows of remarkable stochastic character, but in long term and global view, it shows of distinct regularity character. Normally, the movement trend of the stock price can be imitated and learned. Actually, it is a complicated function of scheduling. Artificial neural network can approach any continuous function precisely by adjusting connection weights, so it can also approach the securities price function which changes along with time. This paper analyses the BP algorithm in detail, including the number of hidden layer, the amount of neural node and training algorithm. In order to improve the training speed, this paper adopts the automatic and adaptive step to perfect the BP algorithm. In addition, because the traditional BP neural network is easy to trap into local minimum, this paper makes use of the characteristic of simulated annealing algorithm and let it unite with BP algorithm. Because the simulated annealing algorithm can get optimal approximation by searching local, it can help BP algorithm not to trap into local minimum. Meanwhile, this paper also discusses the disposal of inputted data, choice of forecasting method and so on. Besides, based on the designed algorithm, this paper designs a forecasting system about the movement trend of stock price in the platform of the Microsoft Visual Studio .NET 2003. At last, this paper uses the system to forecast themovement trend of stock price about YUNNAN Copper and gets a satisfying result—70% of prediction is correct. This paper presents a new algorithm by putting simulated annealing algorithm and the BP algorithm together. The new algorithm overcomes the shortcoming of traditional BP algorithm which is easy to trap into local minimum. Also, this new algorithm provides a new idea and researching method about the stock forecast and proves itself with theoretical and practical values.