A mutual association based nonlinear ensemble mechanism for time series forecasting

被引:15
作者
Adhikari, Ratnadip [1 ]
机构
[1] LNM Inst Informat Technol, Dept Comp Sci & Engn, Jaipur 302031, Rajasthan, India
关键词
Time series forecasting; Combining multiple forecasts; Nonlinear ensemble; Accuracy improvement; Box-Jenkins models; Artificial neural networks; ARTIFICIAL NEURAL-NETWORK; FEEDFORWARD NETWORKS; COMBINATION; PERFORMANCE;
D O I
10.1007/s10489-014-0641-y
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Forecasting a time series with reasonable accuracy is an important but quite difficult task that has been attracting lots of research attention for many years. A widely approved fact is that combining forecasts from multiple models significantly improves the forecasting precision as well as often produces better forecasts than each constituent model. The existing literature is accumulated with linear methods of combining forecasts but nonlinear approaches have received very limited research attention, so far. This paper proposes a novel nonlinear forecasts combination mechanism in which the combined model is constructed from the individual forecasts and the mutual dependencies between pairs of forecasts. The individual forecasts are performed through three well recognized models, whereas five correlation measures are investigated for estimating the mutual association between two different forecasts.Empirical analysis with six real-world time series demonstrates that the proposed ensemble substantially reduces the forecasting errors and also outperforms each component model as well as other conventional linear combination methods, in terms of out-of-sample forecasting accuracy.
引用
收藏
页码:233 / 250
页数:18
相关论文
共 41 条
[1]  
Adhikari Ratnadip, 2012, Advances in Knowledge Discovery and Data Mining. Proceedings 16th Pacific-Asia Conference (PAKDD 2012), P38, DOI 10.1007/978-3-642-30217-6_4
[2]   Performance evaluation of weights selection schemes for linear combination of multiple forecasts [J].
Adhikari, Ratnadip ;
Agrawal, R. K. .
ARTIFICIAL INTELLIGENCE REVIEW, 2014, 42 (04) :529-548
[3]   A combination of artificial neural network and random walk models for financial time series forecasting [J].
Adhikari, Ratnadip ;
Agrawal, R. K. .
NEURAL COMPUTING & APPLICATIONS, 2014, 24 (06) :1441-1449
[4]   Persistence in forecasting performance and conditional combination strategies [J].
Aiolfi, Marco ;
Timmermann, Allan .
JOURNAL OF ECONOMETRICS, 2006, 135 (1-2) :31-53
[5]   AN EMPIRICAL-ANALYSIS OF THE ACCURACY OF SA, OLS, ERLS AND NRLS COMBINATION FORECASTS [J].
AKSU, C ;
GUNTER, SI .
INTERNATIONAL JOURNAL OF FORECASTING, 1992, 8 (01) :27-43
[6]   Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition [J].
Andrawis, Robert R. ;
Atiya, Amir F. ;
El-Shishiny, Hisham .
INTERNATIONAL JOURNAL OF FORECASTING, 2011, 27 (03) :672-688
[7]  
[Anonymous], TIME SERIES DATA LIB
[8]  
[Anonymous], 2013, PACIFIC FX DATABASE
[9]  
[Anonymous], 1990 IJCNN INT JOINT
[10]  
[Anonymous], 2001, PRINCIPLES FORECASTI