Towards Dynamic Pricing for Shared Mobility on Demand using Markov Decision Processes and Dynamic Programming

In a Shared Mobility on Demand Service(SMoDS), dynamic pricing plays an important role in the form of an incentive for empowered passengers to decide on the ride offer. Strategies for determining the dynamic tariffs should be suitably designed so that the incurred demand and supply within the SMoDS platform are balanced and therefore economic efficiency is further achieved. In this manuscript, we formulate a discrete time Markov Decision Process (MDP) to determine the probability of acceptance of each empowered passenger that is desired by the SMoDS platform. The proposed MDP formulation is a versatile framework which is shown to explicitly accommodate passenger behavior and realize the desired system objective. Estimated Waiting Time (EWT) is utilized as a suitable metric to measure the balance between demand and supply, with the goal of regulating EWT around a target value. We propose the use of a Dynamic Programming algorithm to derive the optimal policy that achieves the regulation. Computational experiments are conducted to demonstrate effective regulation of EWT, through various scenarios.