BusTr: Predicting Bus Travel Times from Real-Time Traffic
arXiv:2007.00882 · doi:10.1145/3394486.3403376
Abstract
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.
arXiv comment14 pages, 2 figures, 5 tables. Citation: "Richard Barnes, Senaka Buthpitiya, James Cook, Alex Fabrikant, Andrew Tomkins, Fangzhou Xu (2020). BusTr: Predicting Bus Travel Times from Real-Time Traffic. 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. doi: 10.1145/3394486.3403376"
References in corpus (1)
Cited by in corpus (4)
- Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
- A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management
- gtfs2vec -- Learning GTFS Embeddings for comparing Public Transport Offer in Microregions
- Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark