Towards Explainable Anomaly Detection in Shared Mobility Systems

2025-07-21

AI Summary

This study addresses anomaly detection in bike-sharing systems by proposing an interpretable unsupervised framework that fuses heterogeneous multi-source data—including trip records, weather conditions, and public transit information. Methodologically, the framework employs Isolation Forest for fine-grained, station-level anomaly identification and integrates the DIFFI algorithm to quantify the contribution of external factors (e.g., severe weather, traffic restrictions) to detected anomalies, thereby elucidating their causal mechanisms. Compared to conventional single-source models, the proposed approach significantly enhances both robustness and interpretability of anomaly detection. Empirical evaluation on real-world datasets confirms that external environmental factors serve as critical drivers of system-level anomalies. The framework provides actionable technical support and theoretical foundations for data-driven operational optimization and user experience enhancement in shared mobility systems.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Shared mobility systems, such as bike-sharing networks, play a crucial role in urban transportation. Identifying anomalies in these systems is essential for optimizing operations, improving service reliability, and enhancing user experience. This paper presents an interpretable anomaly detection framework that integrates multi-source data, including bike-sharing trip records, weather conditions, and public transit availability. The Isolation Forest algorithm is employed for unsupervised anomaly detection, along with the Depth-based Isolation Forest Feature Importance (DIFFI) algorithm providing interpretability. Results show that station-level analysis offers a robust understanding of anomalies, highlighting the influence of external factors such as adverse weather and limited transit availability. Our findings contribute to improving decision-making in shared mobility operations.

Problem

• Detecting anomalies in shared mobility systems for operational optimization
• Explaining anomalies using multi-source data and interpretable algorithms
• Analyzing external factors' impact on shared mobility system anomalies

Innovation

• Integrates multi-source data for anomaly detection
• Uses Isolation Forest and DIFFI algorithms
• Provides station-level analysis with external factors