Vehicle Rebalancing Under Adherence Uncertainty
For ride-hailing platforms, this work addresses the practical problem of driver non-adherence to rebalancing recommendations, showing large operational gains by modeling dynamic adherence.
Ride-hailing platforms face supply-demand imbalances due to uneven demand and decentralized driver decisions. The proposed Adherence-Aware Vehicle Rebalancing (AAVR) model accounts for evolving driver adherence, improving served demand by 26.72%, reducing waiting time by 26.45%, and increasing platform and driver profits by 25.90% and 28.75% respectively on NYC taxi data.
Ride-hailing platforms frequently face spatiotemporal supply-demand imbalances caused by uneven passenger demand and decentralized driver decision-making. Existing vehicle rebalancing methods typically assume drivers always follow repositioning recommendations or model adherence using static probabilities. In practice, adherence evolves through repeated interactions with the platform. We propose the Adherence-Aware Vehicle Rebalancing (AAVR) model, which generates simultaneous fleet-wide repositioning recommendations while explicitly accounting for driver preferences and dynamically evolving adherence. The resulting optimization problem is computationally intractable, so we derive a tractable upper-bound reformulation that enables real-time recommendation generation for large-scale systems. Simulations on the NYC taxi dataset under dynamic adherence updates show that AAVR consistently outperforms state-of-the-art methods, improving served demand by 26.72%, reducing passenger waiting time by 26.45%, increasing platform and driver profits by 25.90% and 28.75%, respectively, and improving fleet adherence by 30.06%. These results demonstrate that modeling evolving driver adherence improves both operational performance and long-term adherence to platform recommendations.