Stock Market Forecasting Research Based on Neural Network and Pattern Matching

Abstract

BP Neural Networks is one of the most popular tools in the analysis of stock data. Recent research activities in Pattern Matching indicate that Pattern Matching just simplify the complexity of stock trend prediction and provide a simple but effective way for the stock market prediction. This paper analysis the theory of BP Neural Networks and Pattern Matching, proposes a method for combining these two algorithms to establish a stock market forecasting system based on BP Neural Networks and Pattern Matching. This system overcomes the shortcomings of the local least in the Neural Networks forecasting system’s objective function and Pattern Matching System’s lack of stock changing probabilities, takes advantage of the unique strength in stock price forecasting of these two algorithms. Finally, test this system by analyzing and forecasting the Titan Oil’s stock price. The experimental results show that this hybrid system achieves better forecasting accuracy than either of the models used separately. This hybrid system not only has a quick convergent rate and a precise forecast but also that it is easy to use and has much application value.