Time series forecasting using neural networks vs. Box- Jenkins methodology

Abstract

We discuss the results of a comparative study of the performance of neural networks and conventional methods in forecasting time series. Our work was initially inspired by previously published works that yielded inconsistent results about comparative performance. We have experimented with three time series of different complexity using different feed forward, backpropagation neural network models and the standard Box-Jenkins model. Our experiments demonstrate that for time series with long memory, both methods produced comparable results. However, for series with short memory, neural networks outper formed the Box-Jenkins model. We note that some of the comparable results arise since the neural network and time series model appear to be functionally similar models. We have found that for time series of different complexities there are optimal neural network topologies and parameters that enable them to learn more efficiently. Our initial conclusions are that neural networks are robust and provide good long-term forecasting. They are also parsimonious in their data requirements. Neural networks represent a promising alternative for forecasting, but there are problems deter mining the optimal topology and parameters for efficient learning.

References

Bowerman, B.L. and O'Connell, R.T. , 1987, Time Series Forecasting, 2nd. Ed. PWS Publishers, pp. 120.

Fishwick, P.A. , 1989, "Neural Network Models in Simulation: A Comparison with Traditional Modeling Approaches," Proceedings of Winter Simulation Conference, Washington, DC, pp. 702-710.

Kung, S.Y. and Hwang, J.N. , 1988, "An Algebraic Projection Analysis for Optimal Hidden Units Size and Learning Rates in Back-Propagation Learning," Proceedings of IEEE International Neural Network Conference, Vol. II.

Lapedes, A. and Farber, R. , 1987, "Nonlinear Signal Processing Using Neural Network: Prediction and System Modelling," Los Alamos National Lab Technical Report, LA-UR-87 -2662.

Rumelhart, D.E. and McClelland, J.L. ,1986, Parallel Distributed Processing , Vol. 1, MIT Press, Cambridge, Massachusetts.

McClelland, J.L. and Rumelhart, D.E. , 1988, Explorations in Parallel Distributed Processing, MIT Press, Cambridge, Massachusetts.

Newton, H.J. , 1988. TIMESLAB: A Time Series Analysis Laboratory, Wadsworth & Brooks/Cole Publishing Company, California.

Sharda, R. and Patil, R.B. , 1990, "Neural Networks as Forecasting Experts : An Empirical Test," Proceedings of the IJCNN Meeting, Washington, pp. 491-494.