Utilizing Machine Learning for Identification of Financial Fraud in the Healthcare Sector

Abstract

Health and financial data are collected by the healthcare business. Due to electronic payment improvements, financial fraud monitoring has become expensive for healthcare service providers. Thus, fraud detection requires ongoing development. This study proposes the ensemble fraud detection classifier to increase performance. Ensemble classifiers use many machine learning detection algorithms. The evaluation focuses on accuracy, precision, and recall metrics. In a side-by-side comparison, the proposed ensemble classifiers excel beyond NB, RF, and KNN. Specifically, the ensemble method boasts an accuracy of 99.46, precision of 98.38, and a recall of 98.58, surpassing other classifiers. Future work in this study aims to integrate a hybrid model tailored to address imbalances in datasets and real-time responsiveness in financial transactions with improved accuracy.