Data-Driven Competitor-Aware Positioning in On-Demand Vehicle Rental Networks

We study a novel operational problem that considers vehicle positioning in on-demand rental networks, such as car sharing in the wider context of a competitive market in which users select vehicles based on access. Existing approaches consider networks in isolation; our competitor-aware model takes supply situations of competing networks into account. We combine online machine learning to predict market-level demand and supply with dynamic mixed integer nonlinear programming. For evaluation, we use discrete event simulation based on real-world data from Car2Go and DriveNow. Our model outperforms conventional models that consider the fleet in isolation by a factor of two in terms of profit improvements. In the case we study, the highest theoretical profit improvements of 7.5% are achieved with a dynamic model. Operators of on-demand rental networks can use our model under existing market conditions to build a profitable competitive advantage by optimizing access for consumers without the need for fleet expansion. Model effectiveness increases further in realistic scenarios of fleet expansion and demand growth. Our model accommodates rising demand, defends against competitors' fleet expansion, and enhances the profitability of own fleet expansions.