BusTr: Predicting Bus Travel Times from Real-Time Traffic
This work addresses the need for accurate bus delay predictions in public transit systems lacking official real-time tracking, offering incremental improvements for users of services like Google Maps.
The paper tackles the problem of predicting bus travel times from real-time traffic data, presenting BusTr, a neural sequence model that improves over the state-of-the-art baseline DeepTTE by reducing MAPE by 30% and enhancing training stability.
We present BusTr, a machine-learned model for translating road traffic forecasts into predictions of bus delays, used by Google Maps to serve the majority of the world's public transit systems where no official real-time bus tracking is provided. We demonstrate that our neural sequence model improves over DeepTTE, the state-of-the-art baseline, both in performance (-30% MAPE) and training stability. We also demonstrate significant generalization gains over simpler models, evaluated on longitudinal data to cope with a constantly evolving world.