Scope
In (Müller et al, 2024) the authors investigate a dynamic pricing approach for free-floating car-sharing systems. The study aims to minimise the need for operator-initiated vehicle relocations by rebalancing car distribution through location-dependent pricing. The model uses historical data and stochastic dynamic programming to predict future vehicle movements and determine optimal prices, which in turn reduces the volume of emissions.
Summary
In general, free-floating car-sharing providers face a major challenge: the imbalance of vehicle distribution caused by uneven travel patterns. This results in an accumulation of cars at popular destinations and a lack of cars at popular origins. As a result, the system can no longer meet demand and may lose customers. Motivated by this, the authors provide a data-driven model to predict future vehicle movements and the expected profit of each vehicle. They use optimisation tools to combine various data sources and result in different prices for the same vehicle for different customers, depending on their location. Overall, this process leads to a rebalancing of the cars in the pickup/drop-off zone without the operator having to relocate cars, which means that the number of emissions decreases.
The model finds optimal prices by calculating expected profit after a customer arrives, using the technique of stochastic dynamic programming. To improve tractability, certain simplification assumptions are made to approximate the values for expected future profit. At the same time, historical data is used with information about the location of various cars, the time when they were picked up, and the profit they generated until the end of the day. The historical car values are then weighted according to their spatial and temporal similarity. To illustrate the approach, this work also carried out simulations and a case study within the city of Vienna. The results of these studies confirm the benefits of this customer-centric dynamic pricing approach, which outperforms all considered benchmarks significantly, particularly regarding realised profits and the spatial distribution of vehicles.
Relevance for EXIGENCE
(Müller et al, 2024) work illustrates a particular application domain, that of car sharing systems, where dynamic pricing can be helpful in reducing emissions, and therefore in reducing the carbon footprint of the entire car sharing system. The paper calculates dynamic prices so as to incentivize users towards a more energy-efficient behavior, leading to reducing unnecessary movements of cars from one location to another.
- Müller, J. Gönsch, L. Albrecht, and M. Staskiewicz. “Dynamic Pricing for Car-Sharing Systems Reduces CO2 Emissions”, Sustainability/Amplify, 2024.
