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

TL;DR

This paper introduces an ensemble hypernetwork approach to learn personalized driver utility functions in ride-hailing systems, capturing non-linear preferences and improving prediction accuracy over traditional linear models.

Contribution

It develops a novel ensemble hypernetwork method that dynamically models individual driver preferences, enhancing prediction and interpretability in ride-hailing decision modeling.

Findings

Improved prediction accuracy of driver decisions.

Effective uncertainty estimation and model robustness.

Revealed personalized driver preferences and attribute impacts.

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.