A First Look at Predictability and Explainability of Pre-request Passenger Waiting Time in Ridesharing Systems

2025-08-12

AI Summary

This paper addresses the underexplored problem of predicting “pre-request waiting time”—the duration passengers wait before submitting ride requests—in ride-hailing platforms. Unlike existing approaches that rely on driver-matching information, we propose the first systematic solution based solely on supply-demand dynamics. We design FiXGBoost, a feature-interaction-enhanced XGBoost model that integrates spatiotemporal patterns, supply-demand imbalance metrics, and user behavioral signals. To ensure interpretability, we quantify the contribution of each factor via post-hoc analysis. Evaluated on over 30 million real-world trip records, FiXGBoost achieves statistically significant improvements in prediction accuracy over state-of-the-art baselines. Moreover, its transparent, factor-wise explanations provide actionable insights for both passenger trip planning and platform-level dynamic dispatch optimization—thereby enhancing both user experience and operational efficiency.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Passenger waiting time prediction plays a critical role in enhancing both ridesharing user experience and platform efficiency. While most existing research focuses on post-request waiting time prediction with knowing the matched driver information, pre-request waiting time prediction (i.e., before submitting a ride request and without matching a driver) is also important, as it enables passengers to plan their trips more effectively and enhance the experience of both passengers and drivers. However, it has not been fully studied by existing works. In this paper, we take the first step toward understanding the predictability and explainability of pre-request passenger waiting time in ridesharing systems. Particularly, we conduct an in-depth data-driven study to investigate the impact of demand&supply dynamics on passenger waiting time. Based on this analysis and feature engineering, we propose FiXGBoost, a novel feature interaction-based XGBoost model designed to predict waiting time without knowing the assigned driver information. We further perform an importance analysis to quantify the contribution of each factor. Experiments on a large-scale real-world ridesharing dataset including over 30 million trip records show that our FiXGBoost can achieve a good performance for pre-request passenger waiting time prediction with high explainability.

Problem

• Predict pre-request passenger waiting time in ridesharing
• Understand demand-supply impact on waiting time
• Develop explainable model without driver information

Innovation

• Feature interaction-based XGBoost model
• Demand-supply dynamics impact analysis
• Explainable pre-request waiting time prediction