Art der Publikation: Beitrag in Zeitschrift

Customer-Centric Dynamic Pricing for Free-Floating Vehicle Sharing Systems

Autor(en):

Müller, C.; Gönsch, J.; Soppert, M.; Steinhardt, C.

Titel der Zeitschrift:

Transportation Science

Jahrgang (Veröffentlichung):

57 (2023)

Heftnummer:

6

Seiten:

1406-1432

Schlagworte:

Free-Floating Shared Mobility System, Customer-Centric Dynamic Pricing, DataDriven Non-Parametric Value Function Approximation

Digital Object Identifier (DOI):

doi:10.1287/trsc.2021.0524

Link zum Volltext:

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3987196

Zitation:

Download BibTeX

Kurzfassung

Free-floating shared mobility systems offer customers the flexibility to pick up and drop off vehicles at any location within the business area and, thus, have become the most popular type of shared mobility system. However, this flexibility has the drawback that vehicles tend to accumulate at locations with low demand. To counter these imbalances, pricing has proven to be an effective and cost-efficient means. The fact that customers use mobile applications, combined with the fact that providers know the exact location of each vehicle in real-time, provides new opportunities for dynamic pricing.

In this context, we develop a pricing approach for the dynamic online problem of a provider who determines profit-maximizing prices whenever a customer opens the provider’s mobile application to rent a vehicle. Our pricing approach has three distinguishing features: First, it is customer-centric, i.e., it considers the customer’s location as well as disaggregated choice behavior to precisely capture the effect of price and walking distance to the available vehicles on the customer’s propensity to choose a vehicle. Second, our pricing approach is origin-based, i.e., prices are differentiated by location and time of rental start, which reflects the real-world situation where the rental destination is usually unknown. Third, our approach is anticipative and uses a stochastic dynamic program to anticipate the effect of current decisions on future vehicle locations, rentals, and profits. As solution method, we propose a non-parametric value function approximation, which offers several advantages for the application, e.g., historical data can readily be used and main parameters can be pre-computed such that the online pricing problem becomes tractable. Extensive numerical studies, including a case study based on Share Now data, demonstrate that our approach increases profits by up to 13% compared to existing approaches from the literature and other benchmarks.