文献类型：会议论文

英文题名：Stock Price Trend Prediction Model Based on WNN with Redundant Structure Reduced by RS

作者：Ren Shuili[1];Lou Yuanwei[2];Lei Lei[3]

第一作者：Ren Shuili

通讯作者：Ren, SL[1]

机构：[1]XiJing Coll, Xian 710123, Shaanxi, Peoples R China;[2]Air Force Engn Univ, Air Traff Control & Nav Coll, Xian 710051, Shaanxi, Peoples R China;[3]Henan Univ Econ & Law, Sch Business Adm, Zhengzhou 050046, Henan, Peoples R China

第一机构：XiJing Coll, Xian 710123, Shaanxi, Peoples R China

通讯机构：[1]corresponding author), XiJing Coll, Xian 710123, Shaanxi, Peoples R China.

会议论文集：International Conference on Education, Economics and Management Research (ICEEMR)

会议日期：MAY 29-31, 2017

会议地点：Singapore, SINGAPORE

语种：英文

外文关键词：Wavelet Neural Network; Rough Set; Stock Price Prediction; Structure Optimization

摘要：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.