Ridesharing with Driver Location Preferences

Duncan  Rheingans-Yoo; Scott Duke Kominers; Hongyao  Ma; David C. Parkes

Article | Proceedings of the International Joint Conference on Artificial Intelligence | 2019

Ridesharing with Driver Location Preferences

by Duncan Rheingans-Yoo, Scott Duke Kominers, Hongyao Ma and David C. Parkes

Abstract

We study revenue-optimal pricing and driver compensation in ridesharing platforms when drivers have heterogeneous preferences over locations. If a platform ignores drivers' location preferences, it may make inefficient trip dispatches; moreover, drivers may strategize so as to route towards their preferred locations. In a model with stationary and continuous demand and supply, we present a mechanism that incentivizes drivers to both (i) report their location preferences truthfully and (ii) always provide service. In settings with unconstrained driver supply or symmetric demand patterns, our mechanism achieves (full-information) first-best revenue. Under supply constraints and unbalanced demand, we show via simulation that our mechanism improves over existing mechanisms and has performance close to the first best.

Keywords: ridesharing; pricing; Compensation and Benefits; Geographic Location; Market Design; Mathematical Methods;

Format: Print

Read Now

Citation:

Rheingans-Yoo, Duncan, Scott Duke Kominers, Hongyao Ma, and David C. Parkes. "Ridesharing with Driver Location Preferences." Proceedings of the International Joint Conference on Artificial Intelligence (2019): 557–564.

COVID-19 convalescent plasma (CCP) therapy is currently a leading treatment for COVID-19. At present, there is a shortage of CCP relative to demand. We develop and analyze a model of centralized CCP allocation that incorporates both donation and distribution. In order to increase CCP supply, we introduce a mechanism that utilizes two incentive schemes, respectively based on principles of “paying it backward" and “paying it forward." Under the first scheme, CCP donors obtain treatment vouchers that can be transferred to patients of their choosing. Under the latter scheme, patients obtain priority for CCP therapy in exchange for a future pledge to donate CCP if possible. We show that in steady-state, both principles generally increase overall treatment rates for all patients—not just those who are voucher-prioritized or pledged to donate. Our results also hold under certain conditions if a fraction of CCP is reserved for patients who participate in clinical trials. Finally, we examine the implications of pooling blood types on the efficiency and equity of CCP distribution.

We prove configuration results for extremal Type II codes, analogous to the configuration results of Ozeki and of the second author for extremal Type II lattices. Specifically, we show that for n ∈{8,24,32,48,56,72,96} every extremal Type II code of length n is generated by its codewords of minimal weight. Where Ozeki and Kominers used spherical harmonics and weighted theta functions, we use discrete harmonic polynomials and harmonic weight enumerators. Along the way we introduce "t12-designs" as a discrete analog of Venkov's spherical designs of the same name.

Faculty & Research

Ridesharing with Driver Location Preferences

Abstract

Citation:

About the Author

More from the Author