Neural networks and seasonality: Some technical considerations

Abstract Debate continues regarding the capacity of feedforward neural networks (NNs) to deal with seasonality without pre-processing. The purpose of this paper is to provide, with examples, some theoretical perspective for the debate. In the first instance it considers possible specification errors arising through use of autoregressive forms. Secondly, it examines seasonal variation in the context of the so-called ‘universal approximation’ capabilities of NNs, finding that a short (bounded) sinusoidal series is easy for the network but that a series with many turning points becomes progressively more difficult. This follows from results contained in one of the seminal papers on NN approximation. It is confirmed in examples which also show that, to model seasonality with NNs, very large numbers of hidden nodes may be required.

[1]  Ah Chung Tsoi,et al.  Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[2]  E. C. Titchmarsh,et al.  The theory of functions , 1933 .

[3]  B. Curry,et al.  Neural networks, linear functions and neglected non-linearity , 2003, Comput. Manag. Sci..

[4]  C. Micchelli,et al.  Approximation by superposition of sigmoidal and radial basis functions , 1992 .

[5]  Bruce Curry.  Parameter redundancy in neural networks: an application of Chebyshev polynomials , 2007, Comput. Manag. Sci..

[6]  Shin'ichi Tamura,et al.  Capabilities of a four-layered feedforward neural network: four layers versus three , 1997, IEEE Trans. Neural Networks.

[7]  H. White,et al.  There exists a neural network that does not make avoidable mistakes , 1988, IEEE 1988 International Conference on Neural Networks.

[8]  Jochen J. Steil.  Local stability of recurrent networks with time-varying weights and inputs , 2002, Neurocomputing.

[9]  Malcolm J. Beynon,et al.  Comparing neural network approximations for different functional forms , 1999, Expert Syst. J. Knowl. Eng..

[10]  Bruce Curry,et al.  Model selection in Neural Networks: Some difficulties , 2006, Eur. J. Oper. Res..

[11]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[12]  Vera Kurková,et al.  Kolmogorov's theorem and multilayer neural networks , 1992, Neural Networks.

[13]  N. A. Diamantidis,et al.  An interactive tool for knowledge base refinement , 1999, Expert Syst. J. Knowl. Eng..

[14]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[15]  Denise R. Osborn,et al.  The Econometric Analysis of Seasonal Time Series , 2001 .

[16]  Guoqiang Peter Zhang,et al.  Neural network forecasting for seasonal and trend time series , 2005, Eur. J. Oper. Res..