BusTr: Predicting Bus Travel Times from Real-Time Traffic

Of these two modalities, the world's public transit systems where no official real-time real-time state is disproportionately important for the bus tracking is provided. We demonstrate that our neural routine trips that dominate most people's transportation sequence model improves over DeepTTE, the state-ofthe-art needs. Most transit users know by heart the routes connecting baseline, both in performance ( 30% MAPE) and their home, work, and other frequent destinations, training stability. We also demonstrate significant generalization but they have a well-established need for information gains over simpler models, evaluated on longitudinal about real-time changes. Transit variability is a data to cope with a constantly evolving world.