Abstract
Among the various potential applications of neural networks, forecasting is considered to be a major application. Several researchers have reported their experiences with the use of neural networks in forecasting, and the evidence is inconclusive. This paper presents the results of a forecasting competition between a neural network model and a Box-Jenkins automatic forecasting expert system. Seventy-five series, a subset of data series which have been used for comparison of various forecasting techniques, were analysed using the Box-Jenkins approach and a neural network implementation. The results show that the simple neural net model tested on this set of time series could forecast about as well as the Box-Jenkins forecasting system.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
AFS Inc. (1988)AUTOBOX Software User Manual, Automatic Forecasting Systems, Hatboro, PA.
Box, G. E. P. and Jenkins, G. M. (1976)Time Series Analysis: Forecasting and Control, Holden-Day, San Francisco, CA.
Fishwick, P. (1989) Neural network models in simulation: a comparison with traditional modeling approaches, inProceedings of Winter Simulation Conference. Washington, DC, pp. 702–10.
Fozzard, R., Bradshaw, G. and Ceci, L. (1989) A connectionist expert system for solar flare forecasting, inAdvances in Neural Information Processing Systems I, Touretzky, D. S. (ed.), Morgan Kaufmann Publishers, Inc., San Mateo, CA, pp. 264–71.
Lapedes, A. and Farber, R. (1987) Nonlinear signal processing using neural networks: prediction and system modeling,Los Alamos National Lab Technical Report LA-UR-87-2261, July.
Makridakis, S., Anderson, A., Carbone, R., Fildes, R., Hibdon, M., Lewandowski, R., Newton, J., Parzen, E. and Winkler, R. (1982) The accuracy of extrapolation (time series) methods: results of a forecasting competition.Journal of Forecasting,1, 111–53.
McClelland, J. and Rumelhart, D. (1988)Exploration in Parallel Distributed Processing: A Handbook of Models, Programs and Exercises, The MIT Press, Cambridge, MA.
Pack, D. J. and Downing, D. J. (1983) Why didn't Box-Jenkins win (again)?, in3rd International Symposium on Forecasting, Philadelphia.
Sharda, R. and Ireland, T. (1987) An empirical test of automatic forecasting systems,ORSA/TIMS Meeting, New Orleans, May.
Sharda, R. and Patil, R. (1990) Neural networks as forecasting experts: an empirical test, inProceedings of the International Joint Conference on Neural Networks, IJCNN-WASH-D.C., Jan. 15–19,II, pp. 491–4.
Smolensky, P. (1986) Neural and conceptual interpretation of PDP models, inParallel Distributed Processing, Vol. 2, McClelland, J. L. and Rumelhart, D. L. and the PDP Research Group (eds), MIT Press, Cambridge, MA, p. 397.
Sutton, R. S. (1988) Learning to predict by the methods of temporal differences.Machine Learning,3, 9–44.
Tang, Z., de Almedia, C. and Fishwick, P. A. (1990) Time series forecasting using neural networks vs. Box-Jenkins methodology,International Workshop on Neural Networks, Feb. 2–4, Auburn, AL.
Werbos, P. (1974) Beyond regressions: new tools for prediction and analysis in the behavioral sciences, PhD Thesis, Harvard University, MA.
Werbos, P. (1988) Generalization of back propagation with application to recurrent gas market model.Neural Networks,1, 339–56.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sharda, R., Patil, R.B. Connectionist approach to time series prediction: an empirical test. J Intell Manuf 3, 317–323 (1992). https://doi.org/10.1007/BF01577272
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01577272