Pricing in Ride-hailing Platforms with Strategic Drivers

Abstract:

In this work, we study optimal pricing in a two-sided marketplace with strategic drivers who decide when to enter or exit the market and where to work in order to maximize their long-run average utility. The platform sets prices anticipating these strategic responses and seeks to maximize revenue subject to the induced driver behavior.

To address this problem, we first develop a fluid model that characterizes equilibrium flow rates and drivers’ strategic decisions. We show that drivers’ equilibrium strategies admit a tractable structure: participation and relocation decisions depend on local congestion and demand conditions, as well as a network-wide highest utility for drivers that govern whether drivers are willing to stay, relocate, or exit. Leveraging this structure, we formulate an optimization problem that jointly determines optimal prices, equilibrium flow rates, and the highest attainable utility in the network for drivers.

Using the equilibrium strategy derived from the fluid model, we then construct a corresponding stochastic policy. We show that the revenue achieved under fluid-optimal prices provides a strong approximation to the performance of the stochastic system, and that fluid-optimal prices are near optimal in simulation for large-scale systems.

Bio:

Sha Chen is a PhD candidate at Northwestern University. She received her B.Eng. in Automation from South China University of Technology in 2014 and her M.S. in Control Science and Engineering from Tsinghua University in 2017. Her research interests include pricing, control, and equilibrium analysis in service systems. She has published work in IISE Transactions and IEEE Transactions on Automatic Control. Her paper was selected as a Featured Article in IISE Transactions and received the Best Paper Award in the Supply Chain and Logistics Focus Issue (2025).