Enhancing Medicare Fraud Detection Through Machine Learning

Abstract

Medicare fraud is one of the major challenges faced by the healthcare industry, leading to significant financial losses and reduced trust in healthcare systems. Traditional fraud detection methods mainly rely on manual auditing and rule-based systems, which are often inefficient in detecting complex and evolving fraudulent activities. This project proposes an intelligent Medicare fraud detection system using machine learning techniques to improve the accuracy and efficiency of identifying fraudulent healthcare claims. The system analyzes historical medical claim data and applies various machine learning algorithms such as Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine to classify claims as fraudulent or legitimate. Data preprocessing, feature selection, and class balancing techniques are used to enhance model

performance. The proposed model helps in detecting suspicious billing patterns, abnormal claim behavior, and provider fraud with reduced human intervention. Experimental results demonstrate that machine learning-based approaches provide higher accuracy, faster detection, and better scalability compared to traditional methods. The developed system can assist healthcare organizations and insurance providers in minimizing financial losses and improving the reliability of Medicare services.