# Learning-Based Pricing and Matching for Two-Sided Queues

arXiv: https://arxiv.org/abs/2403.11093 · HTML: https://mlsanity.com/paper/2403.11093/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 17 Mar 2024.

## Builds on (most cited first, 7 of 7)

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Dynamic Type Matching](https://mlsanity.com/paper/1811.07048/) (2018)
- [An online learning approach to dynamic pricing and capacity sizing in service systems](https://mlsanity.com/paper/2009.02911/) (2020)
- [Dynamic Pricing and Matching for Two-Sided Queues](https://mlsanity.com/paper/1911.02213/) (2019)
- [Near Optimal Control in Ride Hailing Platforms with Strategic Servers](https://mlsanity.com/paper/2008.03762/) (2020)
- [Matching Impatient and Heterogeneous Demand and Supply](https://mlsanity.com/paper/2102.02710/) (2021)
- [Non-asymptotic near optimal algorithms for two sided matchings](https://mlsanity.com/paper/2207.11656/) (2022)

## Built on by (most cited first, 1 of 1)

- [Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets](https://mlsanity.com/paper/2510.14097/) (2025)

## Abstract (arXiv)

We consider a dynamic system with multiple types of customers and servers. Each type of waiting customer or server joins a separate queue, forming a bipartite graph with customer-side queues and server-side queues. The platform can match the servers and customers if their types are compatible. The matched pairs then leave the system. The platform will charge a customer a price according to their type when they arrive and will pay a server a price according to their type. The arrival rate of each queue is determined by the price according to some unknown demand or supply functions. Our goal is to design pricing and matching algorithms to maximize the profit of the platform with unknown demand and supply functions, while keeping queue lengths of both customers and servers below a predetermined threshold. This system can be used to model two-sided markets such as ride-sharing markets with passengers and drivers. The difficulties of the problem include simultaneous learning and decision making, and the tradeoff between maximizing profit and minimizing queue length. We use a longest-queue-first matching algorithm and propose a learning-based pricing algorithm, which combines gradient-free stochastic projected gradient ascent with bisection search. We prove that our proposed algorithm yields a sublinear regret tildeO(T5/6) and anytime queue-length bound tildeO(T1/6), where T is the time horizon. We further establish a tradeoff between the regret bound and the queue-length bound: tildeO(T1-γ) versus tildeO(Tγ) for γ ∈ (0, 1/6].