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

Authors

  • Zheng Fang School of Economics & Management, Nanjing University of Science & Technology, Nanjing, Jiangsu 210094, China
  • Chaoshin Chiao Department of Finance, National Dong Hwa University, Hualien, Taiwan Corresponding address: No. 200, Xiaolingwei Street, Nanjing, Jiangsu 210094, China

Abstract

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.

Keywords: Back-Propagation neural network, support vector machine, stock price prediction, financial indicators

Cite As

Z. Fang and C. Chiao, “Stock Price Prediction Based on a Neural Network Model and Data Miningâ€
Engineering Intelligent Systems, vol. 28 no. 2, pp. 179-183, 2020.



Downloads

Published

2020-09-01

Issue

Vol. 28 No. 3 (2020): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.