# BusTr: Predicting Bus Travel Times from Real-Time Traffic

arXiv: https://arxiv.org/abs/2007.00882 · HTML: https://mlsanity.com/paper/2007.00882/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities](https://mlsanity.com/paper/2202.03630/) (2022)
- [A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management](https://mlsanity.com/paper/2306.02806/) (2023)
- [gtfs2vec -- Learning GTFS Embeddings for comparing Public Transport Offer in Microregions](https://mlsanity.com/paper/2111.00960/) (2021)
- [Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark](https://mlsanity.com/paper/2106.16046/) (2021)
- [STContext: A Multifaceted Dataset for Developing Context-aware Spatio-temporal Crowd Mobility Prediction Models](https://mlsanity.com/paper/2501.03583/) (2025)
- [UniTE -- The Best of Both Worlds: Unifying Function-Fitting and Aggregation-Based Approaches to Travel Time and Travel Speed Estimation](https://mlsanity.com/paper/2104.13321/) (2021)
- [Public Transit Arrival Prediction: a Seq2Seq RNN Approach](https://mlsanity.com/paper/2210.01655/) (2022)
- [Short Run Transit Route Planning Decision Support System Using a Deep Learning-Based Weighted Graph](https://mlsanity.com/paper/2308.12828/) (2023)

## Abstract (arXiv)

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.