Abstract

With the overall increase in the elderly population come additional, necessary medical needs and costs. Medicare is a U.S. healthcare program that provides insurance, primarily to individuals 65 years or older, to offload some of the financial burden associated with medical care. Even so, healthcare costs are high and continue to increase. Fraud is a major contributor to these inflating healthcare expenses. Our paper provides a comprehensive study leveraging machine learning methods to detect fraudulent Medicare providers. We use publicly available Medicare data and provider exclusions for fraud labels to build and assess three different learners. In order to lessen the impact of class imbalance, given so few actual fraud labels, we employ Logistic Regression creating two class distributions. Our results show that the other algorithms have poor performance compared with Logistic Regression. Learners have the best fraud detection performance, particularly for the 80:20 class distributions with average AUC scores, respectively, and low false negative rates. We successfully demonstrate the efficacy of employing machine learning Models to detect Medicare fraud.

Description