AN INTEGRATED MODEL USING WAVELET DECOMPOSITION AND LEAST SQUARES SUPPORT VECTOR MACHINES FOR MONTHLY CRUDE OIL PRICES FORECASTING

被引:12
作者
Bao, Yejing [1 ,2 ]
Zhang, Xun [2 ]
Yu, Lean [2 ]
Lai, Kin Keung [3 ]
Wang, Shouyang [2 ]
机构
[1] Beijing Univ Technol, Coll Pilot, Dept Econ & Management, Beijing 101101, Peoples R China
[2] Chinese Acad Sci, Acad Math & Syst Sci, Inst Syst Sci, Beijing 100190, Peoples R China
[3] City Univ Hong Kong, Dept Management Sci, Kowloon, Hong Kong, Peoples R China
基金
中国国家自然科学基金;
关键词
Crude oil price forecasting; Haar a trous wavelet transform; least squares support vector machines; hybrid model;
D O I
10.1142/S1793005711001949
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
In this paper, a hybrid model integrating wavelet decomposition and least squares support machines (LSSVM) is proposed for crude oil price forecasting. In this model, the Haar a trous wavelet transform is first selected to decompose an original time series into several sub-series with different scales. Then the LSSVM is used to predict each sub-series. Subsequently, the final oil price forecast is obtained by reconstructing the results of the sub-series forecasts. The experimental results show that the integrated model, based on multi-scale wavelet decomposition, outperforms the traditional single-scale models. Furthermore, the proposed hybrid model is the best among all the models compared in this study. To fully integrate the advantages of several models, a combined forecasting model is presented. The study shows that the combined forecasting model is clearly better than any individual model for crude oil price forecasting.
引用
收藏
页码:299 / 311
页数:13
相关论文
共 26 条
[1]  
Aussem A., 1997, Connection Science, V9, P113, DOI 10.1080/095400997116766
[2]   A COMPARISON OF PETROLEUM FUTURES VERSUS SPOT PRICES AS PREDICTORS OF PRICES IN THE FUTURE [J].
BOPP, AE ;
LADY, GM .
ENERGY ECONOMICS, 1991, 13 (04) :274-282
[3]   Support vector machine with adaptive parameters in financial time series forecasting [J].
Cao, LJ ;
Tay, FEH .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (06) :1506-1518
[4]   Practical method for determining the minimum embedding dimension of a scalar time series [J].
Cao, LY .
PHYSICA D, 1997, 110 (1-2) :43-50
[5]   ARIMA models to predict next-day electricity prices [J].
Contreras, J ;
Espínola, R ;
Nogales, FJ ;
Conejo, AJ .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2003, 18 (03) :1014-1020
[6]   Modelling the world oil market:: Assessment of a quarterly econometric model [J].
Dees, Stephane ;
Karadeloglou, Pavlos ;
Kaufmann, Robert K. ;
Sanchez, Marcelo .
ENERGY POLICY, 2007, 35 (01) :178-191
[7]  
Gestel V. T., 2001, IEEE T NEURAL NETWOR, V12, P809, DOI DOI 10.1109/72.935093
[8]  
Gulen SG, 1998, J ENERGY FINANCE DEV, V3, P13
[9]  
He ZJ, 2005, LECT NOTES COMPUT SC, V3611, P324
[10]  
HUNTINGTON HG, 1994, ENERGY J, V15, P1