Article ID: | iaor19972391 |
Country: | Netherlands |
Volume: | 13 |
Issue: | 1 |
Start Page Number: | 43 |
End Page Number: | 50 |
Publication Date: | Jan 1997 |
Journal: | International Journal of Forecasting |
Authors: | Kirby Howard R., Dougherty Mark S., Watson Susan M. |
Keywords: | forecasting: applications, neural networks |
This article discusses the relative merits of neural networks and time series methods for traffic forecasting and summarises the findings from a comparative study of their performance for motorway traffic in France. Whilst it was possible to get a good performance with both neural networks and traditional Auto-Regressive Integrated Moving Average (ARIMA) models when forecasting up to an hour ahead using data supplied in 30-min intervals, a purpose-built pattern based forecasting model known as ATHENA, developed by INRETS, out-performed both these methods somewhat. The ways in which these models relate to the structure of traffic data are discussed and alternative paradigms are proposed.