Nan Ma
College of Information Technology, Beijing Union University, Beijing, 100101,China
Yun Zhai
E-Government Research Center, Chinese Academy of Governance, Beijing, 100089, China
Wen-Fa Li
College of Information Technology, Beijing Union University, Beijing, 100101,China
Cui-Hua Li
Department of GSH Information-Based, Military Office in Beijing, Beijing, 100840, China
Shan-shan Wang
College of Information Technology, Beijing Union University, Beijing, 100101,China
Lin Zhou
College of Information Technology, Beijing Union University, Beijing, 100101,China
ABSTRACT
Neural network algorithm is very suitable for stock prediction as a model for dealing with complicated relationship. However, the prediction accuracy of neural network algorithm depends largely on the number of hidden nodes and the terminal condition. To follow up the changes in stock prices, a new method is proposed in this study to find out the optimal parameter. The recommended solution is setting fewer hidden nodes and lower holdout percentage. Results show that the proposed method can lessen about 60% of the forecast error such that it can ensure the efficiency and accuracy of the algorithm.
PDF References Citation
Received: June 03, 2013;
Accepted: October 06, 2013;
Published: November 13, 2013
How to cite this article
Nan Ma, Yun Zhai, Wen-Fa Li, Cui-Hua Li, Shan-shan Wang and Lin Zhou, 2013. Neural Network Algorithm Based Method for Stock Price Trend Prediction. Journal of Applied Sciences, 13: 5384-5390.
DOI: 10.3923/jas.2013.5384.5390
URL: https://scialert.net/abstract/?doi=jas.2013.5384.5390
DOI: 10.3923/jas.2013.5384.5390
URL: https://scialert.net/abstract/?doi=jas.2013.5384.5390
REFERENCES
- Isaksson, M., D. Wisell and D. Ronnow, 2005. Wide-band dynamic modeling of power amplifiers using radial-basis function neural networks. IEEE Trans. Microwave Theo. Tech., 53: 3422-3428.
CrossRef - Isaksson, M., D. Wisell and D. Ronnow, 2005. Nonlinear behavioral modeling of power amplifiers using radial-basis function neural networks. Proceedings of the International Microwave Symposium Digest, June 12-17, 2005, Long Beach, CA.
CrossRef - Naskas, N. and Y. Papananos, 2004. Neural-network-based adaptive baseband predistortion method for RF power amplifiers. Trans. Circuit. Syst. Ii-Exp. Briefs, 51: 619-623.
CrossRefDirect Link - Wu, W., W.Q. Chen and B. Liu, 2001. Prediction of ups and downs of stock market by BP neural networks. J. Dalian Univ. Technol., 41: 9-15.
Direct Link