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

The authors discuss the results of a comparative study of the performance of neural networks and conventional methods in forecasting time series. The present work was initially inspired by previously published works that yielded inconsistent results about comparative performance. The authors have experimented with three time series of different complexity using different feed forward, backpropagation neural network models and the standard Box-Jenkins model. The present experiments demonstrate that for time series with long memory, both methods produced comparable results. However, for series with short memory, neural networks outperformed the Box-Jenkins model. The authors note that some of the comparable results arise since the neural network and time series model appear to be functionally similar models. They have found that for time series of different complexities there are optimal neural network topologies and parameters that enable them to learn more efficiently. The 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 determining the optimal topology and parameters for efficient learning.