An ARIMA‐ANN Hybrid Model for Time Series Forecasting

Li Wang; Haofei Zou; Jia Su; Ling Li; Sohail Chaudhry

doi:10.1002/sres.2179

journal article May 01, 2013

An ARIMA‐ANN Hybrid Model for Time Series Forecasting

Li Wang

Haofei Zou Jia Su

Ling Li

Sohail Chaudhry

Systems Research and Behavioral Science Vol. 30 No. 3 pp. 244-259 · Wiley

View at Publisher Save 10.1002/sres.2179

Abstract

Autoregressive integrated moving average (ARIMA) model has been successfully applied as a popular linear model for economic time series forecasting. In addition, during the recent years, artificial neural networks (ANNs) have been used to capture the complex economic relationships with a variety of patterns as they serve as a powerful and flexible computational tool. However, most of these studies have been characterized by mixed results in terms of the effectiveness of the ANNs model compared with the ARIMA model. In this paper, we propose a hybrid model, which is distinctive in integrating the advantages of ARIMA and ANNs in modeling the linear and nonlinear behaviors in the data set. The hybrid model was tested on three sets of actual data, namely, the Wolf's sunspot data, the Canadian lynx data and the IBM stock price data. Our computational experience indicates the effectiveness of the new combinatorial model in obtaining more accurate forecasting as compared to existing models. Copyright © 2013 John Wiley & Sons, Ltd.

Topics

No keywords indexed for this article. Browse by subject →

References

46

[1]

The Combination of Forecasts

J. M. Bates, C. W. J. Granger

Journal of the Operational Research Society 10.1057/jors.1969.103

[2]

Box G (1970)

[3]

10.2307/2345277

[4]

10.1002/(sici)1099-1743(200003/04)17:2<149::aid-sres290>3.0.co;2-q

[5]

10.1080/17517575.2012.698022

[6]

10.1016/0169-2070(89)90012-5

[7]

10.1109/tii.2012.2188804

[8]

10.1016/s0925-2312(98)00076-9

[9]

10.1111/1468-0394.00117

[10]

Ginzburg I (1993)

[11]

Hipel K (1994)

[12]

10.1016/s0360-8352(98)00066-7

[13]

10.1016/s0360-8352(02)00036-0

[14]

10.1002/sres.967

[15]

10.1007/s005210200021

[16]

10.1016/0925-2312(95)00020-8

[17]

10.1111/1468-0394.00118

[18]

10.1016/s0377-2217(99)00376-8

[19]

10.1109/titb.2012.2198317

[20]

10.1016/0925-5273(96)00039-4

[21]

The accuracy of extrapolation (time series) methods: Results of a forecasting competition

S. Makridakis, A. Andersen, R. Carbone et al.

Journal of Forecasting 10.1002/for.3980010202

[22]

10.1002/for.3980110806

[23]

Patterson D (1996)

[24]

Pelikan E "Power consumption in West‐Bohemia: improved forecasts with decorrelating connectionist networks" Neural Network World (1992)

[25]

10.1007/978-1-4684-6318-7

[26]

10.2307/2552350

[27]

10.1007/s00521-003-0391-y

[28]

10.1111/j.1468-0394.1996.tb00119.x

[29]

10.1016/s0957-4174(98)00030-x

[30]

10.1287/ijoc.5.4.374

[31]

Trippi R (1996)

[32]

10.1016/s0167-9236(98)00028-1

[33]

10.1016/s0040-1625(00)00113-x

[34]

10.1016/0143-8174(87)90030-8

[35]

WangJ LeuJ.1996.Stock market trend prediction using ARIMA‐based neural networks.Proceedings of IEEE International Conference on Neural Networks 1996 pp.2160–2165.

[36]

10.1016/j.eswa.2009.06.104

[37]

10.1016/0925-2312(95)00021-6

[38]

10.1016/s0378-7206(98)00050-0

[39]

10.1002/(sici)1099-1743(200003/04)17:2<103::aid-sres286>3.0.co;2-r

[40]

10.1016/s0950-7051(01)00110-1

[41]

10.1109/titb.2011.2178034

[42]

Time series forecasting using a hybrid ARIMA and neural network model

G.Peter Zhang

Neurocomputing 10.1016/s0925-2312(01)00702-0

[43]

10.1016/s0169-2070(97)00044-7

[44]

10.1016/s0950-7051(01)00102-2

[45]

10.1109/tii.2012.2197004

[46]

10.1016/j.eswa.2007.06.023

Metrics

136

Citations

46

References

Details

Published: May 01, 2013
Vol/Issue: 30(3)
Pages: 244-259
License: View

Authors

L

Li Wang

School of Economics and Management Beihang University Beijing China

H

Haofei Zou

China International Engineering Consulting Corporation Beijing China

J

Jia Su

Telecommunication Planning Research Institute of MII Beijing China

L

Ling Li

Old Dominion University Norfolk VA USA

S

Sohail Chaudhry

Villanova University Villanova PA USA

Cite This Article

Li Wang, Haofei Zou, Jia Su, et al. (2013). An ARIMA‐ANN Hybrid Model for Time Series Forecasting. Systems Research and Behavioral Science, 30(3), 244-259. https://doi.org/10.1002/sres.2179

An ARIMA‐ANN Hybrid Model for Time Series Forecasting

You May Also Like