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

TL;DR

This paper presents a novel reinforcement learning-based matching algorithm for Lyft that improves real-time driver-rider matching, increasing efficiency, driver earnings, and platform revenue.

Contribution

It introduces the first real-time learning matching algorithm for ridesharing, significantly enhancing matching efficiency and revenue.

Findings

Enabled drivers to serve millions more riders annually.

Generated over $30 million in incremental revenue per year.

Successfully deployed globally in 2021.

Abstract

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 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.