Analysis of Fraud Detection Mechanism in Health Insurance Using Statistical Data Mining Techniques Pravin R. Bagde 1 , Manoj S. Chaudhari 2 1 PG Student, Department of CSE, PBCE Nagpur, India 2 Professor & HOD, Department of CSE, PBCE Nagpur, India Abstract - Health insurance fraud increases the disorganization and unfairness in our society. Health care fraud leads to substantial losses of money and very costly to health care insurance system. It is horrible because the percentage of health insurance fraud keeps increasing every year in many countries. To address this widespread problem, effective techniques are in need to detect fraudulent claims in health insurance sector. The application of data mining is specifically relevant and it has been successfully applied in medical needs for its reliable precision accuracy and rapid beneficial results. This paper aims to provide a comprehensive survey of the statistical data mining methods applied to detect fraud in health insurance sector. Keywords - health insurance, fraud detection, data mining, statistical methods. I. INTRODUCTION Insurance fraud is a significant and costly problem for both policyholders and insurance companies in all sectors of the insurance industry. India is one of the fastest growing economies in the world, has a burgeoning middle class, and has witnessed a significant rise in the demand for health insurance products. Over the last 10 years, the health insurance industry has grown at a capital annual compounded growth rate of around 20%. However, with the exponential growth in the industry, there has also been an increased incidence of frauds in the country. Health Insurance fraud encompasses a wide range of illicit practices and illegal acts involving intentional deception or misrepresentation. Data mining has a tremendous impact in improving healthcare fraud detection system. Data mining has been applied to fraud detection in both the way i.e. supervised and non-supervised manner. Data mining techniques and its application for fraud detection in health care sector is described below. II. DATA MINING TECHNIQUES & ITS APPLICATION In today’s world there is huge amount of data stored in real world databases and this amount continues to grow fast. Traditional methods of detecting health care fraud and abuse are time-consuming and inefficient. So, there is a need for semi-automatic methods that discover the hidden knowledge in such database. Data mining is a core of the KDD process. Data mining automatically filtering through immense amounts of data to find known or unknown patterns bring out valuable new perceptions and make predictions. Data mining techniques has been used intensively and extensively by many healthcare organizations for fraud detection. A. Data Mining Techniques Data mining techniques tend to learn models from data. There are two approaches on learning the data mining models. One is supervised learning & second is unsupervised learning they are described below: Supervised methods are usually used for classification and prediction objectives including traditional statistical methods such as regression analysis, discriminant analysis, neural networks, Bayesian networks and Support Vector Machine (SVM). Supervised learning methods attempt to discover the relationship between input variable and an output variable. Unsupervised methods are usually used for description including association rules extraction such as Apriori algorithm and segmentation methods such as clustering and anomaly detection. Unsupervised learning methods are applied when no prior information of the dependant variable is available for use. B. Application of Data Mining: Data mining holds great potential for the healthcare industry to enable health systems to systematically use data and analytics to identify inefficiencies and best practices that improve care and reduce costs. Data mining brings a set of tools and techniques that can be applied to this processed data to discover hidden patterns that provide healthcare professionals an additional source of knowledge for making decisions [2]. Data mining application can greatly benefit all parties involved in the health care industry. For example data mining can help healthcare insurers to detect fraud and abuse; health care organization can make customer relationship management decision; Physicians can identify effective treatments and best practices; and patients receive better and more affordable healthcare services. Pravin R. Bagde et al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 7 (2) , 2016, 925-927 www.ijcsit.com 925