Time series forecasting using artificial neural networks methodologies: A systematic review

Abstract

This paper studies the advances in time series forecasting models using artificial neural network methodologies in a systematic literature review. The systematic review has been done using a manual search of the published papers in the last 11 years (2006–2016) for the time series forecasting using new neural network models and the used methods are displayed. In the covered period in the study, the results obtained found 17 studies that meet all the requirements of the search criteria. Only three of the obtained proposals considered a process different to the autoregressive of a neural networks model. These results conclude that, although there are many studies that presented the application of neural network models, but few of them proposed new neural networks models for forecasting that considered theoretical support and a systematic procedure in the construction of model. This leads to the importance of formulating new models of neural networks.