《计算机应用研究》|Application Research of Computers

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

New Approach of Shortterm Stock Prediction Based on Combination of PhaseSpace Reconstruction Theory and Recurrent Neural Network

免费全文下载 (已被下载 次)  
获取PDF全文
作者 马千里,郑启伦,彭宏,钟谭卫
机构 1.华南理工大学 计算机科学与工程学院,广东 广州 510640;2.华南农业大学 理学院,广东 广州 510640
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2007)04-0239-03
DOI 10.3969/j.issn.1001-3695.2007.04.072
摘要 根据股票指数时间序列复杂的非线性特性,提出以相空间重构理论与递归神经网络相结合的股票短期预测新方法。以相空间重构理论确定最佳延迟时间和最小嵌入维数,以最佳延迟时间为间隔的最小嵌入维数作为递归神经网络的输入维数,并按预测相点步进递归的生成训练数据进行短期预测,提高了预测精度和稳定性。该方法应用于沪市股票综合指数预测,其结果与传统的单纯用BP网络模型预测的结果相比较,精度大大提高,证明了该预测模型和方法在实际时间序列预测领域的有效性和实用性。
关键词 股票短期预测;时间序列;相空间;神经网络
基金项目 国家自然科学基金资助项目(30230350); 广东省科技攻关项目(2005B10101033)
本文URL http://www.arocmag.com/article/1001-3695(2007)04-0239-03.html
英文标题 New Approach of Shortterm Stock Prediction Based on Combination of PhaseSpace Reconstruction Theory and Recurrent Neural Network
作者英文名 MA Qian-li, ZHENG Qi-lun, PENG Hong, ZHONG Tan-wei
机构英文名 1. School of Computer Science & Engineering, South China University of Technology, Guangzhou Guangdong 510640, China; 2. College of Science, South China Agricultural University, Guangzhou Guangdong 510640, China
英文摘要 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.
英文关键词
参考文献 查看稿件参考文献
 
收稿日期
修回日期
页码 239-241
中图分类号
文献标志码 A