Neural Network Models for Time Series Forecasts

Tim Hill, Marcus O'Connor and William Remus
Additional contact information
Tim Hill: University of Hawaii, 2404 Maile Way, Honolulu, Hawaii 96822
Marcus O'Connor: University of New South Wales, Kensington, New South Wales, Australia
William Remus: University of Hawaii, 2404 Maile Way, Honolulu, Hawaii 96822

Management Science, 1996, vol. 42, issue 7, 1082-1092

Abstract: Neural networks have been advocated as an alternative to traditional statistical forecasting methods. In the present experiment, time series forecasts produced by neural networks are compared with forecasts from six statistical time series methods generated in a major forecasting competition (Makridakis et al. [Makridakis, S., A. Anderson, R. Carbone, R. Fildes, M. Hibon, R. Lewandowski, J. Newton, E. Parzen, R. Winkler. 1982. The accuracy of extrapolation (time series) methods: Results of a forecasting competition. J. Forecasting 1 111--153.]); the traditional method forecasts were estimated by experts in the particular technique. The neural networks were estimated using the same ground rules as the competition. Across monthly and quarterly time series, the neural networks did significantly better than traditional methods. As suggested by theory, the neural networks were particularly effective for discontinuous time series.

Keywords: neural networks; time series; back propagation (search for similar items in EconPapers)
Date: 1996
References: Add references at CitEc
Citations: View citations in EconPapers (49)

Downloads: (external link)
http://dx.doi.org/10.1287/mnsc.42.7.1082 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormnsc:v:42:y:1996:i:7:p:1082-1092

Access Statistics for this article

More articles in Management Science from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().