Abstract: Fraud is widely spread and it can be very costly to the health- care insurance system. It involves intentional deception intended to result in an unauthorized benefit. It is shocking because the incidence of health insurance fraud increasing every year. In order to detect and avoid the fraud, data mining techniques are applied. This includes some basic knowledge about health care system and its behaviors, analysis of the health care insurance data. Data mining is divided into two learning techniques, supervised and unsupervised learning is employed to detect fraud claims. But, since each of the above techniques has its own advantages and disadvantages, by combining the advantages of both the techniques, a hybrid approach for detecting fraud claims in healthcare insurance industry is proposed.So, to make healthcare insurance industry free from fraud, it is necessary to focus on the elimination of fake claims arriving through health insurance. According to the recent survey, it is found that the number of false claims in the industry is near about 15 percent of total claims. Insurance companies in USA losses over 30 billion USD annually to healthcare insurance frauds. The statistics is increasing in developing country like India as well.

Keywords: Database, Data Mining, web Application, ECM