Fraud Auditor: A Visual Analytics Approach for Collusive Fraud in Health Insurance
Journal of Computing in Education, Sports and Health · 2025
DOI: 10.69996/jcesh.2025011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing in Education, Sports and Health, 2025.
Abstract (Originalsprache)
Collusive fraud in health insurance, involving coordinated deceit by multiple individuals, poses a significant challenge to the integrity of healthcare systems. Traditional fraud detection techniques often fall short in identifying such sophisticated patterns due to the subtle similarities between fraudulent and legitimate claims and the scarcity of labeled data. To address these challenges, this paper presents FraudAuditor, a novel three-stage visual analytics approach designed to detect and analyze collusive fraud in health insurance data. The system begins by enabling users to interactively construct a co-visit network that models patient visit relationships. It then applies an enhanced community detection algorithm that incorporates fraud-likelihood scoring to identify suspicious groups. Finally, the visual interface empowers domain experts to investigate, compare, and validate behaviors over different timeframes, aiding in decision-making and reducing false positives. Real-world case studies validate the system’s effectiveness and usability, demonstrating its potential as a powerful tool for insurance auditors to detect organized fraud proactively and efficiently.
Zitieren
APA
(2025). Fraud Auditor: A Visual Analytics Approach for Collusive Fraud in Health Insurance. Journal of Computing in Education, Sports and Health. https://doi.org/10.69996/jcesh.2025011
Vancouver
Fraud Auditor: A Visual Analytics Approach for Collusive Fraud in Health Insurance. Journal of Computing in Education, Sports and Health. 2025. doi:10.69996/jcesh.2025011
BibTeX
@article{euvimed2025,
title = {Fraud Auditor: A Visual Analytics Approach for Collusive Fraud in Health Insurance},
journal = {Journal of Computing in Education, Sports and Health},
year = {2025},
doi = {10.69996/jcesh.2025011}
}
EUVIMED