Balancing Profit and Traveller Acceptance in Ride-Pooling Personalised Fares

2025-08-28

AI Summary

Heterogeneous user price sensitivity in ride-pooling services impedes simultaneous optimization of platform profitability and rider acceptance. Method: We propose a personalized dynamic pricing framework integrating explicit modeling of individual value of travel time (VOTT) with adaptive machine learning. Our approach estimates user-specific price acceptance thresholds via predictive models and employs a daily-updating online optimization algorithm to generate real-time, differentiated fare quotes. Concurrently, it selects high-value ride-pooling combinations while preserving rider utility. Contribution/Results: Empirical evaluation demonstrates >90% accuracy in predicting user acceptance behavior within ten days. The method significantly increases platform profit, reduces low-efficiency trips, and enhances both system-wide operational efficiency and demand attractiveness—achieving a Pareto-improvement in service quality and economic performance.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: The sharing economy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Ride-pooling systems, to succeed, must provide an attractive service, namely compensate perceived costs with an appealing price. However, because of a strong heterogeneity in a value-of-time, each traveller has his own acceptable price, unknown to the operator. Here, we show that individual acceptance levels can be learned by the operator (over $90%$ accuracy for pooled travellers in $10$ days) to optimise personalised fares. We propose an adaptive pricing policy, where every day the operator constructs an offer that progressively meets travellers' expectations and attracts a growing demand. Our results suggest that operators, by learning behavioural traits of individual travellers, may improve performance not only for travellers (increased utility) but also for themselves (increased profit). Moreover, such knowledge allows the operator to remove inefficient pooled rides and focus on attractive and profitable combinations.

Problem

• Learning individual traveler price acceptance for personalized fares
• Optimizing ride-pooling fares to balance profit and traveler utility
• Removing inefficient pooled rides through behavioral trait analysis

Innovation

• Adaptive pricing policy learning individual acceptance levels
• Personalized fares optimizing profit and traveler utility
• Removing inefficient pooled rides focusing profitable combinations