<-上一篇/Previous Article 下一篇/Next Article->

[1]吴朝阳.小波变换和GM-ARMA组合模型的股指预测[J].智能系统学报,2011,6(3):279-282.
　WU Zhaoyang.Using wavelet transformation and a GM-ARMA model to forecast stock index[J].CAAI Transactions on Intelligent Systems,2011,6(3):279-282.

点击复制

小波变换和GM-ARMA组合模型的股指预测

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 6 期数: 2011年第3期页码: 279-282 栏目: 学术论文—智能系统出版日期: 2011-06-25

Title:: Using wavelet transformation and a GM-ARMA model to forecast stock index

文章编号:: 1673-4785(2011)03-0279-04

作者:: 吴朝阳; 康考迪亚大学统计与数学系，蒙特利尔H3G 2H9

Author(s):: WU Zhaoyang; The Department of Mathematics and Statistics, Concordia University, Montreal H3G 2H9, Canada

关键词:: 小波分解; 灰色模型; ARMA模型; GM-ARMA模型; 股指预测

Keywords:: wavelet decomposition; grey model; ARMA model; GM-ARMA model; stock prediction

分类号:: TP18

文献标志码:: A

摘要:: 当前在利用小波分解和其他模型建立组合模型的过程中，对小波基方程的选择和分解层数并没有一个标准，基本上是通过经验和一些实验来决定这2个因素；而且很多利用小波分解建立的组合模型并不考虑模型之间相互的影响，对各个子模型的参数估计采取各自独立的估计，从而导致预测结果不是最优. 为此，提出了先对小波基方程和分解层数这2个特征进行参数化, 然后定量地对所有子模型的特征参数进行统一、综合的评估，以达到建立最佳组合模型的目的. 由于该组合模型是由小波分解、灰色模型和ARMA模型组合而成的，因此称为WGM-ARMA模型. 股指预测的实例验证了WGM-ARMA模型大幅度地降低了预测误差，说明了该组合模型的有效性、实用性和可行性.

Abstract:: During the process of building a hybrid model by combining wavelet decomposition and other techniques, there is no standard in terms of selecting a wavelet base function and decomposition level. The commonly used ways are usually based on the researcher’s experience or several experiments instead of a quantitative approach. In addition, many hybrid models based on wavelet decomposition do not consider the interaction between sub models. Instead of estimating the parameters in all sub models as the whole, they estimate the parameters separately, which lead to that the prediction result is not optimal. In order to solve this problem, this paper first introduced two new parameters, wavelet functions and decomposition levels, then quantitatively estimated all the parameters as a whole for the purpose of building an optimal hybrid model. For convenience, the model was called the WGM-ARMA model because it combines the wavelet decomposition, grey model, as well as autoregressive integrated moving average (ARMA) model. Experimental results show that the hybrid model significantly reduces prediction errors. As a result, it can be concluded that the model in terms of forecasting stock index is valid and useful, along with the method used to construct the optimal hybrid model. 

参考文献/References:: ［1］朱宁,徐标,仝殿波.上证指数的时间序列预测模型［J］.桂林电子工业学院学报, 2006, 26(2): 124128.
ZHU Ning, XU Biao, TONG Dianbo. Timeseries prediction model of Shanghai composite index［J］. Journal of Guilin University of Electronic Technology, 2006, 26(2): 124128.
［2］POTERBA J M, SUMMERS L H. The persistence of volatility and stock market fluctuations［J］. American Economic Review, 1986, 76(5): 11431151.
［3］FRENCH K R, SCHWERT G W, STAMBAUGH R F. Expected stock returns and volatility［J］. Journal of Financial Economics, 1987, 19(1): 329.
［4］李国平,于广青,陈森发.中国股票价格灰色预测研究综述［J］.东南大学学报:哲学社会科学版, 2005, 7(2): 2830, 126.
LI Guoping, YU Guangqing, CHEN Senfa. A review of research on stock price gray forecast in China［J］. Journal of Southeast University: Philosophy and Social Science, 2005, 7(2): 2830, 126.
［5］郭宁,向凤红.灰色理论和神经元网络在证券市场中的应用［J］.自动化技术与应用， 2008， 27(10)： 13.
GUO Ning, XIANG Fenghong. Application of grey model and neural network in the stockmarket［J］. Techniques of Automation and Applications, 2008, 27(10)： 13.
［6］吴庚申,梁平,龙新峰.基于GM-ARMA的年电力负荷组合模型［J］.湖北电力, 2005, 29(2): 2123.
WU Gengshen, LIANG Ping, LONG Xinfeng. An annual electric consumption combined model based on GM-ARMA［J］. Hubei Electric Power, 2005, 29(2): 2123.
［7］吴朝阳.改进的灰色模型与ARMA模型的股指预测［J］.智能系统学报, 2010, 5(3): 277281.
WU Zhaoyang. Forecasting stock index based on revised grey model and ARMA model［J］. CAAI Transactions on Intelligent Systems, 2010, 5(3): 277281.
［8］郑纪安.基于小波分析和神经网络的金融时间序列预测研究［D］.厦门：厦门大学, 2009: 4561.
ZHENG Ji’〖KG-*1/3〗an. The research on forecasting of financial time series baesd on wavelet analysis and neural network［D］. Xiamen: Xianmen University, 2009: 4561.
［9］曲文龙,李海燕,刘永伟,等.基于小波和支持向量机的多尺度时间序列预测［J］.计算机工程与应用, 2007, 43(29): 182185.
QU Wenlong, LI Haiyan, LIU Yongwei, et al. Research on multiscale prediction of time series based on wavelet and support vector machines［J］. Computer Engineering and Applications, 2007, 43(29): 182185.
［10］PETERS E E. Fractal market analysis: applying chaos theory to investment and economics［M］. New York, USA: John Wiley and Sons Inc, 1996: 3950.

相似文献/References:: [1]吴朝阳.改进的灰色模型与ARMA模型的股指预测[J].智能系统学报,2010,5(3):277.
　WU Zhao-yang.Forecasting stock indexes based on a revised grey model and the ARMA model[J].CAAI Transactions on Intelligent Systems,2010,5():277.
[2]杨向林,严?? 洪,任兆瑞,等.基于PCA特征和融合特征的ECG身份识别方法[J].智能系统学报,2010,5(5):458.[doi:10.3969/j.issn.1673-4785.2010.05.014]
　YANG Xiang-lin,YAN Hong,REN Zhao-rui,et al.A method based on the PCA feature and fusion feature for ECG human identification[J].CAAI Transactions on Intelligent Systems,2010,5():458.[doi:10.3969/j.issn.1673-4785.2010.05.014]

备注/Memo

收稿日期： 2010-09-18.
通信作者：吴朝阳.E-mail:hostingca@gmail.com.
作者简介：吴朝阳，男，1975年生，工程师，主要研究方向为灰色系统理论、时间序列和小波变换的股票预测.

更新日期/Last Update: 2011-07-23

小波变换和GM-ARMA组合模型的股指预测 PDF下载HTML

备注/Memo

小波变换和GM-ARMA组合模型的股指预测

PDF下载 HTML