Combining predictive schemes in short-term traffic forecasting

The principal motivation for combining forecasts which can either be a clas s label (classification) or numerical (regression) has been to avoid the a priori choice of which forecasting method to use by attempting to aggregate all the information which each forecasting model embodies. In selecting th e 'best' model, the forecaster is often discarding useful independent evide nce in those models which are rejected. Hence the methodology of combining forecasts is founded upon the axiom of maximal information usage. Short-term traffic prediction is an area where the combining of two or more predictions is a promising technique which would directly improve the fore cast accuracy. This approach may eventually help in specifying underlying p rocesses more appropriately and thus build better individual models. This article deals with combining forecast methods potentially suitable for short-term prediction with their performance comparisons. The emphasis lie s on the application to the short-term traffic flow prediction. Since the c ombination of predictors has, for the most part, implicitly assumed a stati onary underlying process, attention has been focused on taking into account the effect of nonstationarity of the traffic flow process.