A Better Match for Drivers and Riders: Reinforcement Learning at Lyft

We used reinforcement learning to improve how Lyft matches drivers and riders. The change was implemented globally and led to more than $30 million per year in incremental driver revenue. To better match drivers to riders in our ridesharing application, we revised Lyft’s core matching algorithm. We...

Full description

Saved in:
Bibliographic Details
Published in:INFORMS journal on applied analytics 2024-01, Vol.54 (1), p.71-83
Main Authors: Azagirre, Xabi, Balwally, Akshay, Candeli, Guillaume, Chamandy, Nicholas, Han, Benjamin, King, Alona, Lee, Hyungjun, Loncaric, Martin, Martin, Sébastien, Narasiman, Vijay, Qin, Zhiwei (Tony), Richard, Baptiste, Smoot, Sara, Taylor, Sean, van Ryzin, Garrett, Wu, Di, Yu, Fei, Zamoshchin, Alex
Format: Article
Language:English
Subjects:
Algorithms
Drivers
Earnings
Learning
Matching
Matching concept
Real time
Reinforcement
Ride sharing services
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We used reinforcement learning to improve how Lyft matches drivers and riders. The change was implemented globally and led to more than $30 million per year in incremental driver revenue. To better match drivers to riders in our ridesharing application, we revised Lyft’s core matching algorithm. We use a novel online reinforcement learning approach that estimates the future earnings of drivers in real time, and we use this information to find more efficient matches. This change was the first documented implementation of a ridesharing matching algorithm that can learn and improve in real time. We evaluated the new approach during weeks of switchback experimentation in most Lyft markets and estimated how it benefited drivers, riders, and the platform. In particular, it enabled our drivers to serve millions of additional riders each year, leading to more than $30 million per year in incremental revenue. Lyft rolled out the algorithm globally in 2021.
ISSN:2644-0865
2644-0873
DOI:10.1287/inte.2023.0083