文章摘要
梁坤,张理政.社会媒体环境下基于EMD-DSVR的股票市场预测方法研究[J].安徽建筑大学学报,2016,24(5):106-110
社会媒体环境下基于EMD-DSVR的股票市场预测方法研究
Prediction Method of Stock Market Based on EMD-DSVR under Social Media Environment
  
DOI:10.11921/j.issn.2095-8382.20160519
中文关键词: 经验模态分解  股票收益  混沌理论  支持向量回归
英文关键词: empirical mode decomposition  stock time series  chaos theory  support vector regression
基金项目:国家自然科学基金重点项目(71331002),教育部博士学科点专项科研基金(20120111110027),安徽省软科学重大项目(1302053009)
作者单位
梁坤 合肥工业大学 管理学院合肥 230009 
张理政 安徽建筑大学 管理学院合肥 230022 
摘要点击次数: 6099
全文下载次数: 0
中文摘要:
      现有的利用社会媒体预测股票市场的研究未能考虑股指时间序列所具有的多尺度特征。为了解决这一问题,运用EMD分解法、混沌分析理论和支持向量回归机,提出一种EMD-DSVR股票市场预测方法。首先分析股指时间序列多尺度与社会媒体变量序列多尺度间的内在联系,运用EMD分解法将社会媒体变量序列分解成不同尺度的基本模态分量;然后运用混沌分析理论和支持向量回归机对各模态分量进行建模和预测;最后利用社会媒体变量序列的各模态分量对股票市场进行预测。运用所提出的EMD-DSVR模型,对上证指数和深成指数的日收盘值进行预测,实验结果表明,所提出的方法能有效提高对股指时间序列的预测精度。
英文摘要:
      The existing relevant research of social media-based market performance analysis fails to consider the multi-scale of stock time series. To solve this problem, by employing the empirical mode decomposition (EMD), chaos theory and support vector regression, this paper presents an EMD-DSVR method to predict stock market. First, the intrinsic link between stock time series multi-scale and social media time series multi-scale has been analyzed; and by using EMD method, this paper decomposes the social media time series into many intrinsic modal function (IMF) which can significantly represent potential information of original time serial. Then, by using chaos theory and support vector regression, this paper predicts and sets models for each IMF. Finally, market performance is predicted by using the IMF of social media time series. In order to verify the effectiveness of EMD-DSVR model, the close value of Shanghai Composite Index and Shenzhen component index are predicted by using this model. The results show that our approach can effectively improve the prediction accuracy of stock time series.
查看全文   查看/发表评论  下载PDF阅读器
关闭

分享按钮