Stock Price Prediction Based on a Neural Network Model and Data Mining

摘要

Rapid economic development has stimulated the development of the stock market, and the existence of the stock market has promoted the flow of the market economy. However, the stock market is risky. An effective and accurate stock price prediction tool can significantly reduce the risk of investors and enterprises. This paper briefly introduces the relevant financial indicators of listed companies that can affect stock prices and a support vector machine (SVM) and Back-Propagation (BP) neural network used for predicting stock prices; the trend of the stock price was then predicted using the SVM combined with the BP neural network. The simulation analysis was carried out on the stock price of an A-share listed company using the MATLAB software. The results showed that the stock price prediction model based on SVM and BP needed less training time than the stock price prediction model based solely on BP. Both models could predict the general trend of the stock price, but the SVM and BP-based prediction model were a better fit for the actual values; the mean square, average absolute percentage error, minimum relative error and maximum relative error also reflected that the combination prediction model was more accurate.