主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2014, Vol. 22 ›› Issue (8): 21-28.

• 论文 • 上一篇    下一篇

基于多尺度组合模型的铜价预测研究

王书平, 胡爱梅, 吴振信   

  1. 北方工业大学经济管理学院, 北京 100144
  • 收稿日期:2013-07-07 修回日期:2014-03-12 出版日期:2014-08-20 发布日期:2014-08-23
  • 作者简介:王书平(1977- ),男(汉族),湖南涟源人,北方工业大学经济管理学院,副教授,博士,研究方向:大宗商品定价、计量经济分析.
  • 基金资助:

    北京市属市管高等学校人才强教计划资助项目(PHR20110869);北京市教委学科与研究生教育专项基金(PXM2013_014212_000005)

Forecasting of Copper Price based on Multi-scale Combined Model

WANG Shu-ping, HU Ai-mei, WU Zhen-xin   

  1. School of Economics and Management, North China University of Technology, Beijing 100144, China
  • Received:2013-07-07 Revised:2014-03-12 Online:2014-08-20 Published:2014-08-23

摘要: 铜价预测是国际大宗商品市场研究的一个重要领域。本文运用经验模态分解法(EMD)、人工神经网络(ANN)、支持向量机(SVM)和时间序列方法,基于分解-重构-集成的思想,构建了一个多尺度组合预测模型。在模型构建过程中,提出了运用游程判定法对分量序列进行重构的新思路。然后,运用此模型对LME铜价波动特点和走势进行分析:将铜价序列分解并重构成高频、低频和趋势三个部分,并从不规则因素、重大事件以及长期趋势三个角度解释了重构项的波动特征;实证分析表明,与灰色模型GM(1,1)、Elman神经网络方法等单模型,以及ARIMA-SVM组合模型相比,多尺度组合模型取得了最好的预测效果。

关键词: 多尺度模型, 经验模态分解, 支持向量机, 神经网络, 游程判定法

Abstract: Forecasting of cooper price is an important area of international commodity research. A new multi-scale combined forecasting model is built in this paper by using empirical mode decomposition (EMD), artificial neural network (ANN), support vector machine (SVM) and time series methods based on the idea of decomposition-reconstruction-integration. During the model building process, a new idea to use run length judgment method to reconstruct the component sequences is proposed. Then this model is used to analyze the fluctuation characteristics and trend of LME copper price. Copper price series is decomposed and reconstructed into high frequency, low frequency and trend sequences which can be explained from the angle of irregular factors, major events and long-term trend. Empirical analysis shows that comparing with the gray model GM (1, 1), Elman and some other single models and ARIMA-SVM combined model, multi-scale combined model obtained the best forecasting result.

Key words: multi-scale model, EMD, SVM, ANN, run length judgment method

中图分类号: