Bus Travel Time Predictions Using Additive Models

About

Many factors can affect the predictability of public bus services such as traffic, weather and local events. Other aspects, such as day of week or hour of day, may influence bus travel times as well, either directly or in conjunction with other variables. However, the exact nature of such relationships between travel times and predictor variables is, in most situations, not known. In this paper we develop a framework that allows for flexible modeling of bus travel times through the use of Additive Models. In particular, we model travel times as a sum of linear as well as nonlinear terms that are modeled as smooth functions of predictor variables. The proposed class of models provides a principled statistical framework that is highly flexible in terms of model building. The experimental results demonstrate uniformly superior performance of our best model as compared to previous prediction methods when applied to a very large GPS data set obtained from buses operating in the city of Rio de Janeiro.

Matthias Kormaksson, Luciano Barbosa, Marcos R. Vieira, Bianca Zadrozny · 2014

Related benchmarks

Task	Dataset	Result
Bus arrival time prediction	Bus Route 14 Short distance	MAE (min)1.48	9
Bus arrival time prediction	Bus Route 421 Mid distance	MAE (min)1.32	9
Bus arrival time prediction	Bus Route 110 Mid distance	MAE (min)1.94	9
Bus arrival time prediction	Bus Route 563 Long distance	MAE (min)1.3	9
Bus arrival time prediction	Bus Route 74 Long distance	MAE (min)1.58	9
Bus arrival time prediction	Bus Route 60 Short distance	MAE (min)1.84	9