Review on Data Mining Techniques for Fraud Detection in Health Insurance

Abstract

Review describes an effective method of data mining for health insurance fraud detection that identifies suspicious behavior of health care providers. Fraud and abuse on medical claims became a major concern for health insurance companies last decades. Estimates made for the studied U.S. Medicaid health insurance program is that up to 10% of the claims are fraudulent. Fraud involves intentional deception or misrepresentation intended to result in an unauthorized benefit. It is shocking because the incidence of health insurance fraud keeps increasing every year.
Nowadays there is huge amount of data stored in real world databases and this amount continues to grow fast. So, there is a need for semi-automatic methods that discover the hidden knowledge in such database. Data mining automatically filtering through immense amounts of data to find known/unknown patterns bring out valuable new perceptions and make predictions. Data mining which is divided into two learning techniques viz., supervised and unsupervised is employed to detect fraudulent claims. Basically these techniques are used for fraud detection in health /insurance.