%0 Journal Article
%T New Approach of Short-term Stock Prediction Based on Combination of Phase Space Reconstruction Theory and Recurrent Neural Network<br>基于相空间重构理论与递归神经网络相结合的股票短期预测方法
%A MA Qian-li
%A ZHENG Qi-lun
%A PENG Hong
%A ZHONG Tan-wei
%A <br>马千里
%A 郑启伦
%A 彭宏
%A 钟谭卫
%J 计算机应用研究
%D 2007
%I 
%X A new approach of short-term stock prediction using PSRT(Phase Space Reconstruction Theory) combined with RNN(Recurrent Neural Network) was presented according to the complex nonlinear character of stock time series.The optimal delay time and minimal embedding dimension were determined by PSRT and the input dimension of RNN was decided by minimal embedding dimension.The training samples were generated by means of the stepping recursive phase points,which could improve precision and stability of prediction.The new method was applied to shot-term forecasting of Shanghai stock index.Compared to the traditional standard BP neural network,the results showed higher precision.So this research acquires effective progress in the practical prediction of time series.
%K short-term stock prediction
%K time series
%K phase space
%K neural network<br>股票短期预测
%K 时间序列
%K 相空间
%K 神经网络
%K 相空间重构理论
%K 递归神经网络
%K 结合
%K 股票指数
%K 预测方法
%K Recurrent
%K Neural
%K Network
%K Theory
%K Phase
%K Space
%K Reconstruction
%K Combination
%K Based
%K Prediction
%K Stock
%K 有效性
%K 时间序列预测
%K 预测模型
%K 精度和稳定性
%K 比较
%K 网络模型
%K 结果
%K 指数预测
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=EF4AD2E7BFCF0B30E0823F8BEF8DA788&yid=A732AF04DDA03BB3&vid=B91E8C6D6FE990DB&iid=E158A972A605785F&sid=1DF3F9D75A12D97B&eid=6A73B36E85DB0CE9&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=10