Fraud detection in health insurance using data mining techniques

Fraud is widespread and very costly to the healthcare insurance system. 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. In order to detect and avoid the fraud, data mining techniques are applied. This includes some preliminary knowledge of health care system and its fraudulent behaviors, analysis of the characteristics of health care insurance data. Data mining which is divided into two learning techniques viz., supervised and unsupervised is employed to detect fraudulent claims. But, since each of the above techniques has its own set of advantages and disadvantages, by combining the advantages of both the techniques, a novel hybrid approach for detecting fraudulent claims in health insurance industry is proposed.