Medicare Fraud Detection

This paper explores the development of an intelligent Medicare Fraud Detection System using advanced machine learning and deep learning models. The primary objective is to minimize fraudulent healthcare claims and enhance the efficiency of public fund allocation. The proposed system places a strong emphasis on explainability, transparency, and fairness in its decision-making process. To achieve this, interpretable models such as Random Forest and Decision Trees are employed. Additionally, explainable AI (XAI) tools like SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) are integrated to provide deeper insights into model predictions and ensure stakeholder trust.