Book
Open access
Aug 2026
DSETA: A Dual-Stage Continual Learning Framework for Travel Time Prediction in Dynamic Traffic Environments
This work designs and develops an incrementally updated Dual-Stage ETA prediction framework that has been successfully deployed in DiDi's production environment, processing hundreds of millions of daily requests and validating its strong performance in industrial applications.
Yanming Lyu, Yue Cheng, Lingkun Li et al.
· Proceedings of the 32nd ACM... · 0 citations