Published on: April 2026
MONITORING FRAUD RISK IN INSURANCE CLAIMS
B. Karthik P.Siva Charishma M.Architha D.Kavya
Dr P. Ashok Kumar
Article Status
Available Documents
Abstract
Insurance companies have a problem with fake insurance claims. This makes premiums go up for people who actually need help. It costs the companies a lot of money. The old way of finding claims is not working very well anymore because it takes a long time and people make mistakes. This is happening because insurance is moving to systems very quickly.The goal of this project is to use machine learning to watch out for insurance claims and stop this problem. To do this the system looks at what happens what is strange and how different things are connected, like how much a claim is for what the policy says, if the person has been in an accident before how the customer acts and what the documents say. The system uses old insurance claim information to find claims that do not seem right and might be fake.It uses computer programs like Support Vector Machine, Random Forest, Decision Tree and Logistic Regression to decide if a claim is real or fake. Insurance claims are put into two groups: insurance claims or fake insurance claims. The machine learning techniques help to find the insurance claims by looking at the trends and abnormalities, in insurance claims. This way the system can help insurance companies to stop claims and save money.
How to Cite this Paper
Karthik, B., Charishma, P., M.Architha, & D.Kavya, (2026). Monitoring Fraud Risk in Insurance Claims. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(04). https://doi.org/10.55041/ijcope.v2i4.117
Karthik, B., et al.. "Monitoring Fraud Risk in Insurance Claims." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i4.117.
Karthik, B.,P.Siva Charishma, M.Architha, and D.Kavya. "Monitoring Fraud Risk in Insurance Claims." International Journal of Creative and Open Research in Engineering and Management 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i4.117.
Search & Index
References
[1] Viaene, W., Derrig, R., Baesens, B. And Dedene G. Wrote about comparing methods to detect fake car insurance claims in 2020. They found some techniques that work well. This was published in the Journal of Risk and Insurance volume 69 issue 3 pages 373-421.
[2] Ngai, E. P. K., Hu, Y., Wong, Y. H., Chen, Y. And Sun X. Looked at how data mining can help find fraud in 2021. They wrote about it in Decision Support Systems volume 50 issue 3 pages 559-569.
[3] Bauder, R. And Khoshgoftaar T. M. Did a survey on using machine learning to detect insurance fraud in 2022. They found many different techniques being used. This was published in IEEE Transactions on Big Data volume 8 issue 2 pages 1-15.
[4] Li, X., Liu, J. And Zhao H. Used support vector machines to detect insurance fraud in 2023. They wrote about their findings in Expert Systems with Applications volume 195 pages 116-130.
[5] Zhang Y., Wang, L. And Chen Z. Studied how deep learning can be used to detect insurance fraud in 2024. They thought it was very effective. This was published in IEEE Access, volume 12 pages 34567-34580.
[6] Chen, T. And Guestrin, C. Talked about XGBoost, a way to make tree boosting systems that can handle a lot of data in 2016. This was, at the ACM SIG
[7] V. Chandola, A. Banerjee and V. Kumar wrote about anomaly detection. They said it is a survey on anomaly detection in ACM Computing Surveys, vol. 41, No. 3 Pp. 1–58, 2009.
[8] L. Breiman wrote about forests. He said they are forests of trees, in Machine Learning, vol. 45, No. 1 Pp. 5–32, 2001.
[9] N. Japkowicz and S. Stephen studied the class imbalance problem. They wrote about it in Intelligent Data Analysis, vol. 6, No. 5 Pp. 429–449, 2002. The class imbalance problem is still studied.
Ethical Compliance & Review Process
- •All submissions are screened under plagiarism detection.
- •Review follows editorial policy.
- •Authors retain copyright.
- •Peer Review Type: Double-Blind Peer Review
- •Published on: Apr 07 2026
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.