Fair and Efficient Ridesharing: A Dynamic Programming-based Relocation Approach

2024-01-27

ACM Transactions on Intelligent Systems and Technology

AI Summary

Existing ride-pooling platforms prioritize route recommendations that maximize driver dispatch probability, improving operational efficiency but exacerbating income inequality among drivers; moreover, mainstream fairness-aware studies overlook passengers’ temporal constraints and the sequential nature of ride-pooling assignments. This paper proposes the first dynamic routing recommendation system that jointly optimizes fairness and efficiency. We explicitly incorporate income fairness—quantified via the Gini coefficient—as a primary objective in the routing optimization formulation. Additionally, we design a future-aware driver repositioning mechanism that jointly models destination preferences and spatiotemporal demand forecasts, thereby addressing the temporal sequencing constraints inherent in ride-pooling—a limitation overlooked by conventional matching algorithms. Evaluated on real-world datasets from Washington, D.C., and New York City, our approach improves income fairness by 32% over baseline methods while sustaining an order response rate above 98.5% and preserving platform-level efficiency.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Algorithm Configuration

Application Category

• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Recommending routes by their probability of having a rider has long been the goal of conventional route recommendation systems. While this maximizes the platform-specific criteria of efficiency, it results in sub-optimal outcomes with the disparity among the income of drivers who work for similar time frames. Pioneer studies on fairness in ridesharing platforms have focused on algorithms that match drivers and riders. However, these studies do not consider the time schedules of different riders sharing a ride in the ridesharing mode. To overcome this shortcoming, we present the first route recommendation system for ridesharing networks that explicitly considers fairness as an evaluation criterion. In particular, we design a routing mechanism that reduces the inequality among drivers and provides them with routes that have a similar probability of finding riders over a period of time. However, while optimizing fairness the efficiency of the platform should not be affected as both of these goals are important for the long-term sustainability of the system. In order to jointly optimize fairness and efficiency we consider repositioning drivers with low income to the areas that have a higher probability of finding riders in future. While applying driver repositioning, we design a future-aware policy and allocate the areas to the drivers considering the destination of requests in the corresponding area. Extensive simulations on real-world datasets of Washington DC and New York demonstrate superior performance by our proposed system in comparison to the existing baselines.

Problem

• Balancing fairness and efficiency in ridesharing route recommendations
• Reducing income disparity among drivers over time
• Optimizing driver repositioning based on future rider demand

Innovation

• Dynamic programming for fair driver relocation
• Future-aware policy considering rider destinations
• Joint optimization of fairness and efficiency