WNN Prediction Model of Stock Price with Input Dimensions Reduced by Rough Set

DOI

10.2991/iceemr-17.2017.27How to use a DOI?

Keywords

Wavelet Neural Network, Rough Set, Attribute Reduction, Stock Price, Prediction

Abstract

To improve the prediction ability of stock price, an integration prediction method based on Rough Set (RS) and Wavelet Neural Network (WNN) is proposed. First RS is used to reduce the dimensions of feature of stock price, then the WNN prediction model is established for stock price movement on the basis of feature dimension reduction; finally, the built model is applied to predict the stock price movement. The simulations on daily closing price index of SSE Composite Index indicate that, the proposed method has advantages of simple structure, strong implementation and good prediction accuracy with average correct rate 64%, and gets better stock price prediction in contrast with single neural network, genetic neural network and WNN.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Haiqing Huang
AU  - Yuanwei Lou
AU  - Lei Lei
AU  - Huaping Li
PY  - 2017/05
DA  - 2017/05
TI  - WNN Prediction Model of Stock Price with Input Dimensions Reduced by Rough Set
BT  - Proceedings of the 2017 International Conference on Education, Economics and Management Research (ICEEMR 2017)
PB  - Atlantis Press
SP  - 107
EP  - 110
SN  - 2352-5398
UR  - https://doi.org/10.2991/iceemr-17.2017.27
DO  - 10.2991/iceemr-17.2017.27
ID  - Huang2017/05
ER  -