Auditable Agentic AI for Insurance Claim Fraud Screening
DOI:
https://doi.org/10.5281/d59rmr27Keywords:
Agentic Fraud Detection, Insurance AI Workflows, Transparent AI Systems, Explainable Fraud Analytics, Claims Validation Processes, Human-Centric AI Governance, Audit Trail Management, Role-Based Access Control, Fraud Detection Architecture, Decision Transparency Frameworks.Abstract
Fraud remains a significant challenge in digital insurance. AI-driven detection models improve efficiency but often function as black boxes, generating alerts that go unvalidated and undermine trust in the system. Agentic AI offers a way to address these shortcomings by extending human-centered concepts of agenda-setting and autonomy to AI agents and workflows, allowing AI systems to act on and carry out decisions within a defined scope of authority. By embedding transparency into the workflow itself, Agentic AI supports the validation of fraud alerts and provides clear, traceable explanations for the decisions made. This framing helps clarify how agentic roles should be defined in fraud detection and in the handling of claims flagged as potentially fraudulent — questions this paper explores through four lenses: What is being done, when, why, and by whom.
We present an architecture built around the key stakeholders in this process — insurance claimants, agents, underwriters, auditors, and regulators — and define their responsibilities, access controls, validation mechanisms, and audit trail requirements. Throughout, the architecture is designed to ensure that human decision-makers retain ultimate authority and accountability, with AI acting in a supporting, transparent role rather than an autonomous one.
References
1. Óskarsdóttir, M., Dendievel, R., Frauenfelder, A., & Heiðarsson, H. (2021). Social network analytics for supervised fraud detection in insurance. Risk Analysis, 42(8), 1872–1890.
2. De Bock, K. W., & Van den Poel, D. (2021). An empirical evaluation of probabilistic classification models for insurance fraud detection. Expert Systems with Applications, 165, 113876.
3. Baesens, B., Höppner, S., & Verdonck, T. (2021). Data engineering for fraud detection. Decision Support Systems, 150, 113492.
4. Srinivas Kalisetty. (2023). Big Data–Driven Cloud Collaboration Models for Enhancing Supplier–Retailer Synchronization in Modern Manufacturing Supply Chains. Journal of Computational Analysis and Applications (JoCAAA), 31(4), 2188–2205. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/4232
5. Bertomeu, J., Cheynel, E., Floyd, E., & Pan, W. (2021). Using machine learning to detect misstatements. Review of Accounting Studies, 26(2), 468–519.
6. Błaszczyński, J., de Almeida Filho, A. T., Matuszyk, A., Szeląg, M., & Słowiński, R. (2021). Auto loan fraud detection using dominance-based rough set approach versus machine learning methods. Expert Systems with Applications, 163, 113740.
7. Pandugula, C., & Nampalli, R. C. R. Optimizing Retail Performance: Cloud-Enabled Big Data Strategies for Enhanced Consumer Insights.
8. Fernández, A., García, S., Herrera, F., & Chawla, N. V. (2021). SMOTE for learning from imbalanced data: Progress and challenges, marking the 15-year anniversary. Journal of Artificial Intelligence Research, 61, 863–905.
9. Gramegna, A., & Giudici, P. (2021). SHAP and LIME: An evaluation of discriminative power in credit risk. Frontiers in Artificial Intelligence, 4, 752558.
10. Gramespacher, T., & Posth, J.-A. (2021). Employing explainable AI to optimize the return target function of a loan portfolio. Frontiers in Artificial Intelligence, 4, 693022.
11. Hadji Misheva, B., Jaggi, D., Posth, J.-A., Gramespacher, T., & Osterrieder, J. (2021). Audience-dependent explanations for AI-based risk management tools: A survey. Frontiers in Artificial Intelligence, 4, 794996.
12. Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2021). Explainable machine learning in credit risk management. Computational Economics, 57, 203–216. Springer Link
13. Hilal, W., Gadsden, S. A., & Yawney, J. (2022). Financial fraud: A review of anomaly detection techniques and recent advances. Expert Systems with Applications, 193, 116429.
14. Pamisetty, V. (2023). Transforming Community Engagement with Generative AI: Harnessing Machine Learning and Neural Networks for Hunger Alleviation and Global Food Security. Journal for Re Attach Therapy and Developmental Diversities.
15. Aslam, F., Hunjra, A. I., Ftiti, Z., Louhichi, W., & Shams, T. (2022). Insurance fraud detection: Evidence from artificial intelligence and machine learning. Research in International Business and Finance, 62, 101744. ScienceDirect
16. Vandervorst, F., Verbeke, W., Vanthienen, J., & Baesens, B. (2022). Data misrepresentation detection for insurance underwriting fraud prevention. Decision Support Systems, 159, 113798. ScienceDirect
17. Kumaraswamy, N., Markey, M. K., Barner, J. C., & Rascati, K. (2022). Feature engineering to detect fraud using healthcare claims data. Expert Systems with Applications, 210, 118433. ScienceDirect
18. Dimri, A., Paul, A., Girish, D., Lee, P., Afra, S., & Jakubowski, A. (2022). A multi-input multi-label claims channeling system using insurance-based language models. Expert Systems with Applications, 202, 117166. ScienceDirec
19. Fritz-Morgenthal, S., Hein, B., & Papenbrock, J. (2022). Financial risk management and explainable, trustworthy, responsible AI. Frontiers in Artificial Intelligence, 5, 779799. Frontiers
20. Reddy, R. (2023). Predictive Health Insights: Ai And Ml's Frontier In Disease Prevention And Patient Management. Available at SSRN.
21. Zhang, C. A., Cho, S., & Vasarhelyi, M. (2022). Explainable artificial intelligence (XAI) in auditing. International Journal of Accounting Information Systems, 46, 100572. ScienceDirect
22. Meske, C., Abedin, B., Klier, M., & Rabhi, F. (2022). Explainable and responsible artificial intelligence. Electronic Markets, 32(4), 2103–2106. Springer Link
23. Černevičienė, J., & Kabašinskas, A. (2022). Review of multi-criteria decision-making methods in finance using explainable artificial intelligence. Frontiers in Artificial Intelligence, 5, 827584. Frontiers
24. Meda, R., & Pamisetty, A. (2023). Intelligent Infrastructure for Real-Time Inventory and Logistics in Retail Supply Chains. Educational Administration: Theory and Practice, 29 (4), 5215–5233.
25. Settipalli, L., & Gangadharan, G. R. (2023). WMTDBC: An unsupervised multivariate analysis model for fraud detection in health insurance claims. Expert Systems with Applications, 215, 119259. ScienceDirect
26. Debener, J., Heinke, V., & Kriebel, J. (2023). Detecting insurance fraud using supervised and unsupervised machine learning. Journal of Risk and Insurance, 90(3), 743–768. Wiley Online Library
27. Hancock, J. T., Bauder, R. A., Wang, H., & Khoshgoftaar, T. M. (2023). Explainable machine learning models for Medicare fraud detection. Journal of Big Data, 10, 154. Springer Link
28. Nabrawi, E., & Alanazi, A. (2023). Fraud detection in healthcare insurance claims using machine learning. Risks, 11(9), 160. MDPI
29. Maiano, L., Montuschi, A., Caserio, M., Ferri, E., Kieffer, F., Germanò, C., Baiocco, L., Ricciardi Celsi, L., Amerini, I., & Anagnostopoulos, A. (2023). A deep-learning-based antifraud system for car-insurance claims. Expert Systems with Applications, 231, 120644. ScienceDirect
30. Zhou, Y., Li, H., Xiao, Z., & Qiu, J. (2023). A user-centered explainable artificial intelligence approach for financial fraud detection. Finance Research Letters, 58, 104309.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2024 Dhanaraj Sathiri (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons
Attribution 4.0 International License (CC BY 4.0).
You are free to:
- Share: copy and redistribute the material
- Adapt: remix, transform, and build upon the material
for any purpose, even commercially.
Under the following terms:
Attribution — You must give appropriate credit to
the original author(s) and source.
Full license text: https://creativecommons.org/licenses/by/4.0/
