Current research on in-vehicle information system, more specifically dynamic route
guidance, is offering the prospect of improved individual trip efficiency by enabling
drivers to avoid recurrent and propagated road congestion. One of the next major
advances in developing route guidance systems will be the short-term prediction of
congestion in road networks. This will inform the driver about the road network
conditions one or two hours in advance and assist them to avoid anticipated
congestion. This paper discusses the application of spatial econometric modelling in
congestion prediction, by using historical Traffic Message Channel (TMC) data stored
in the vehicle navigation unit. The nature of TMC data is in the form of a time series
of geo-referenced congestion warning messages which is generally collected from
vehicles acting as traffic probes. The prediction of future congestion could be based
on the previous year of TMC data. Synthetic TMC data generated by microscopic
traffic simulation for the network of Coventry are used in this study. The feasibility
of using econometric modelling techniques to predict congestion is explored. Results
are presented at the end. The study will add new content to applied spatial
econometrics in the transport field.