Adaptive Dynamic Pricing for Market-based Allocation of Interdependent Commodities

Ongoing digitization of all kinds of human enterprise is allowing sophisticated pricing strategies to be used in domains where previously this has not been feasible. In the mobility domain, commodities such as shared cars or electric vehicle charging services have multiple free parameters that determine their utility to customers. Additionally, sales of individual service items are interdependent, meaning each sale of a service items impacts all consecutive sales. In this thesis, our goal is to concisely describe structure of these commodities and to develop pricing algorithms that improve revenue of service providers and the quality of allocations of these commodities. To this end, we describe the interdependent commodities multi-agent pricing problem model and develop markov decision process based pricing strategy that improves both service provider revenue and resource utilization in the electric vehicle charging domain.