How AI Powers On-Demand Logistics at DoorDash
DoorDash has a three-sided logistics marketplace where the core problem is to identify the most optimal Dasher to fulfill a delivery from a restaurant and bring it to a Consumer. The real-time, quick turnaround nature of DoorDash introduces special challenges: delivery requests come in continuously, Dashers constantly are in movement, and variance in restaurant operations and real-world events (traffic, weather, etc.) have pronounced effects. This talk highlights various AI techniques we use to model these and achieve high marketplace efficiency and quality. These techniques have led to faster deliveries for consumers, higher pay for Dashers, and increased revenue for merchants.
- How AI techniques can be combined with traditional operations research approaches
- Learn ML algorithms used by DoorDash to power on-demand logistics
Raghav Ramesh is the lead machine learning engineer at DoorDash working on its logistics engine, where he focuses on core AI problems: vehicle routing, Dasher assignments, delivery time predictions, demand forecasting, and pricing. Previously, Raghav worked on various data products at Twitter, including recommendation systems, trends ranking, and growth analytics. He holds an MS from Stanford University, where he focused on artificial intelligence and operations research.