Gary Ren, DoorDash
GTC 2020
DoorDash has a complex, three-sided, and real-time marketplace that presents many challenging problems where machine learning has a lot of impact. We'll give an overview of where machine learning is used in DoorDash, and then dive deeper into how we use machine learning to power our logistics engine, which is the system that powers the fulfillment of deliveries. We'll talk about improvements in ML training times between CPU and GPU, as well as single-GPU and multi-GPU. Discover how we tackle the vehicle routing problem with trillions of combinations, delivery time predictions for all your favorite restaurants, and dynamic supply/demand balance.