Model identification and parameter estimation of ARMA models by means of evolutionary algorithms
Susanne Rolf, Joachim Sprave, Wolfgang Urfer · 2002
The field of time series analysis and forecasting methods has significantly changed in the last decade due to the influence of new knowledge in non-linear dynamics. New methods such as artificial neural networks replaced traditional approaches which usually were appropriate for linear models only. Nevertheless, there are still applications where accurate estimations of linear processes, such as ARMA models, are sufficient. However, the methods for this class of models were developed more than 20 years ago, with the restrictions of the, then current, computers in mind. The authors describe an attempt to combine the ideas of the widely used Box-Jenkins method (1970) with new approaches to model identification and parameter estimation based on evolutionary algorithms, a class of probabilistic parameter optimization methods.