Stock Price Trend Prediction Model Based on WNN with Redundant Structure Reduced by RS

DOI

10.2991/iceemr-17.2017.26How to use a DOI?

Keywords

Wavelet Neural Network, Rough Set, Stock Price Prediction, Structure Optimization

Abstract

Due to lots of factors affecting the fluctuation of stock price, it is very difficult to the accurately predict the stock price. For this problem, a Wavelet Neural Network (WNN) stock price prediction method is proposed, and Rough Set (RS) method is introduced to reduce the Input dimensions of WNN and optimize the hidden layer nodes of WNN for optimization structure reduction. The experiment results show that, the introduction of RS attributes reduction can simplify the structure of WNN model can be to a great extent for stock price trend with improvement of the performance. The direction symmetry of prediction corresponding to SSE Composite Index, CSI 300 Index and All Ordinaries Index is 65.75%, 66.37% and 65.93% with 1.7s, 1.8s and 2.1s training time, respectively. The prediction result is better than that of other neural network and WNN models.

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  - Shuili Ren
AU  - Yuanwei Lou
AU  - Lei Lei
PY  - 2017/05
DA  - 2017/05
TI  - Stock Price Trend Prediction Model Based on WNN with Redundant Structure Reduced by RS
BT  - Proceedings of the 2017 International Conference on Education, Economics and Management Research (ICEEMR 2017)
PB  - Atlantis Press
SP  - 103
EP  - 106
SN  - 2352-5398
UR  - https://doi.org/10.2991/iceemr-17.2017.26
DO  - 10.2991/iceemr-17.2017.26
ID  - Ren2017/05
ER  -