Paper Contents
Abstract
Health insurance fraud poses a substantial threat to the integrity of healthcare systems worldwide. Among the most complex and damaging types of fraud is collusive fraud, where multiple actorssuch as patients, healthcare providers, and third-party agentscollaborate to deceive insurance systems. Traditional fraud detection techniques often fail to detect these intricate patterns due to their focus on isolated activities. This paper presents a visual analytics approach for identifying collusive fraud in health insurance claims. Leveraging graph-based modeling, anomaly detection algorithms, and interactive dashboards, the proposed system provides auditors with the tools to uncover suspicious patterns and relationships among entities. By integrating machine learning and human-in-the-loop techniques, the system enables deeper insight into complex fraud networks. Experimental evaluation on real-world datasets demonstrates the system's capability in detecting previously unnoticed fraudulent clusters. The visual interface not only improves fraud detection efficiency but also enhances transparency and decision support for auditors. This work aims to contribute to more resilient and proactive fraud detection mechanisms in the health insurance domain.
Copyright
Copyright © 2025 MALLARAPU POOJITHA. This is an open access article distributed under the Creative Commons Attribution License.
