Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195508,
        author = {Joinoju Naresh Kumar and Utkarsh Pal and Md Amer Khan and Damarla Goutham and Nakka Vinay Kumar Goud},
        title = {Enhancing Healthcare Integrity: A Machine Learning Approach to Medical Insurance Fraud Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {3356-3360},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195508},
        abstract = {Ever since the insurance industry originated, the problem of fraudulent insurance claims has persisted. The insurance market forfeits billions of dollars annually due to these numerous illicit activities, most of which remain undetected. Approximately 600 million rupees are lost every year by the insurance industry in India because of the nation's growing economy, heightened awareness, and superior distribution networks. Annually, deceptive claims lead to losses of 800 crores. India sits 10th regarding gross premiums gathered by life insurance firms and 15th regarding the total revenue produced by non-life sectors. Consequently, we are proposing a structure for selecting features for use in machine learning, enabling the dependable categorization of insurance claims. Avoiding monetary losses and maintaining the trustworthiness of healthcare services relies on identifying fraud within medical insurance claim systems. To successfully spot fraudulent claims, this research examines the application of Support Vector Machines (SVM) combined with GridSearchCV for hyperparameter tuning. To improve model precision, the research processes an extensive dataset of medical insurance claims through strict feature selection and engineering. To locate the optimal hyperparameters for the SVM model, GridSearchCV is utilized to perform a thorough search across defined parameter limits. The model's effectiveness is assessed using metrics such as accuracy, precision, recall, and F1-score. The results demonstrate that, compared to standard models, the tuned SVM model significantly enhances the identification of dishonest claims.},
        keywords = {Medical Insurance Fraud, Support Vector Machines (SVM), GridSearchCV, Hyperparameter Tuning, Feature Selection, Machine Learning, Healthcare Integrity.},
        month = {April},
        }