Evolving Time Series Forecasting Neural Network Models

Abstract

In the last decade, bio-inspired methods have gained an increasing acceptation as alternative approaches for Time Series Forecasting. Indeed, the use of tools such as Artificial Neural Networks (ANNs) and Genetic and Evolutionary Algorithms (GEAs), introduced important features to forecasting models, taking advantage of nonlinear learning and adaptive search. In the present approach, a combination of both paradigms is proposed, where the GEA's searching engine will be used to evolve candidate ANNs topologies, enhancing forecasting models that show good generalization capabilities. A comparison was performed, contrasting bio-inspired and conventional methods, which revealed better forecasting performances, specially when more difficult series were taken into consideration; i.e., nonlinear and chaotic ones.