Learning Personalized Utility Functions for Drivers in Ride-hailing Systems Using Ensemble Hypernetworks

2025-06-21

AI Summary

Ride-hailing drivers’ order-acceptance decisions are governed by nonlinear interactions among order attributes, traffic conditions, and individual preferences—challenging conventional linear random utility models (RUMs) in capturing driver-specific heterogeneity and complex dependencies. To address this, we propose a dynamic personalized modeling framework integrating hypernetworks with ensemble learning: a hypernetwork generates driver-specific, real-time weights for a linear utility function, encoding idiosyncratic preferences; an ensemble architecture trains heterogeneous hypernetworks on multiple data subsets and incorporates controlled stochasticity to enhance generalization and robustness. Our approach jointly achieves high predictive accuracy, model interpretability, and principled uncertainty quantification. Experiments on a large-scale real-world dataset demonstrate statistically significant improvements in order-acceptance prediction accuracy over state-of-the-art baselines, while enabling clear identification of key decision drivers—thereby supporting efficient, transparent, and trustworthy intelligent dispatch systems.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Learning Preferences or Rankings
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In ride-hailing systems, drivers decide whether to accept or reject ride requests based on factors such as order characteristics, traffic conditions, and personal preferences. Accurately predicting these decisions is essential for improving the efficiency and reliability of these systems. Traditional models, such as the Random Utility Maximization (RUM) approach, typically predict drivers' decisions by assuming linear correlations among attributes. However, these models often fall short because they fail to account for non-linear interactions between attributes and do not cater to the unique, personalized preferences of individual drivers. In this paper, we develop a method for learning personalized utility functions using hypernetwork and ensemble learning. Hypernetworks dynamically generate weights for a linear utility function based on trip request data and driver profiles, capturing the non-linear relationships. An ensemble of hypernetworks trained on different data segments further improve model adaptability and generalization by introducing controlled randomness, thereby reducing over-fitting. We validate the performance of our ensemble hypernetworks model in terms of prediction accuracy and uncertainty estimation in a real-world dataset. The results demonstrate that our approach not only accurately predicts each driver's utility but also effectively balances the needs for explainability and uncertainty quantification. Additionally, our model serves as a powerful tool for revealing the personalized preferences of different drivers, clearly illustrating which attributes largely impact their rider acceptance decisions.

Problem

• Predicting driver ride acceptance decisions accurately
• Capturing non-linear attribute interactions and personal preferences
• Balancing explainability and uncertainty in utility prediction

Innovation

• Hypernetworks generate dynamic weights for utility functions
• Ensemble learning improves adaptability and reduces over-fitting
• Model balances explainability and uncertainty quantification effectively