Pricing and Matching Shared Rides

Abstract

Shared rides, which pool individual riders into a single vehicle, are essential for mitigating congestion and promoting more sustainable urban transportation. However, major ridesharing platforms have long struggled to maintain a healthy and profitable shared rides product. The key challenge lies in designing pricing and matching policies that effectively balance platform profitability, rider accessibility, and system efficiency. This research aims to address this challenge through three interconnected research works.The first work tries to address the problem from the perspective of pricing. To understand why shared rides have struggled, we analyze procedures commonly used in practice to set static prices for shared rides, and discuss their pitfalls. We then propose a pricing policy that is adaptive to matching outcomes, dubbed match-based pricing, which varies prices depending on whether a rider is dispatched alone or to what extent she is matched with another rider. Analysis on a single origin-destination setting reveals that match-based pricing is both profit-maximizing and altruistic, simultaneously improving cost efficiency (i.e., the fraction of cost saved by shared rides relative to individual rides) and reducing rider payments relative to the optimal static pricing policy. These theoretical results are validated on a large-scale simulation with hundreds of origin-destinations from Chicago ridesharing data. The improvements in efficiency and reductions in payments are especially noticeable when costs are high and demand density is low, enabling healthy operations where they have historically been most challenging. Whereas the first part assumes that riders are matched to each other pre-trip (i.e., before the rider is dispatched), this neglects a ride's continued matching potential while on-trip after she is initially dispatched solo. The second work develops a dynamic, stochastic matching model where the platform makes both pre-trip and on-trip matching decisions, and contrast the behavior of each phase of matching. Using both synthetic and real-world data from Chicago, we find that whereas pre-trip matching is well-suited to dense downtown areas with concentrated demand, on-trip matching is critical in sparser outskirts where demand is spatially dispersed, and manages a tradeoff between matching opportunity and value. We also embed the matching model in an outer pricing optimization problem to study the interaction of matching with pricing, and find that the addition of on-trip matching increases profitability and efficiency for the platform and lowers prices for riders. These effects are particularly pronounced in the sparse outskirts, where shared rides have historically been most difficult to sustain. The third work complements the analytical and computational contributions with a simulation-based teaching game, Calyber, which is designed to provide hands-on and engaging experience in developing real-time pricing and matching decisions for shared ride services. Students design and implement dynamic pricing and matching policies using a rich historical ridesharing dataset, competing for top performance on a holdout test set. Through this case, students gain practical insight into stochastic dynamic decision-making within a modern, relevant, and data-driven context. Results from previous class implementations provide strong evidence of enhanced learning and engagement. Together, the three works offer a comprehensive treatment of shared ride operations in terms of joint decision making in pricing and matching, spanning modeling analysis, computational methodology, and pedagogical practice.