International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064




Downloads: 108 | Views: 249 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1

Research Paper | Information Technology | India | Volume 4 Issue 4, April 2015 | Rating: 7 / 10


Healthcare Insurance Fraud Detection Leveraging Big Data Analytics

Prajna Dora | Dr. G. Hari Sekharan


Abstract: Health Insurance fraud is a major crime that imposes significant financial and personal costs on individuals, businesses, government and society as a whole. So there is a growing concern among the insurance industry about the increasing incidence of abuse and fraud in health insurance. Health Insurance frauds are driving up the overall costs of insurers, premiums for policyholders, providers and then intern countries finance system. It encompasses a wide range of illicit practices and illegal acts. This paper provides an approach to detect and predict potential frauds by applying big data, hadoop environment and analytic methods which can lead to rapid detection of claim anomalies. The solution is based on a high volume of historical data from various insurance company data and hospital data of a specific geographical area. Such sources are typically voluminous, diverse, and vary significantly over the time. Therefore, distributed and parallel computing tools collectively termed big data have to be developed. Paper demonstrate the effectiveness and efficiency of the open-source predictive modeling framework we used, describe the results from various predictive modeling techniques. The platform is able to detect erroneous or suspicious records in submitted health care data sets and gives an approach of how the hospital and other health care data is helpful for the detecting health care insurance fraud by implementing various data analytic module such as decision tree, clustering and naive Bayesian classification. Aim is to build a model that can identify the claim is a fraudulent or not by relating data from hospitals and insurance company to make health insurance more efficient and to ensure that the money is spent on legitimate causes. Critical objectives included the development of a fraud detection engine with an aim to help those in the health insurance business and minimize the loss of funds to fraud.


Keywords: Big Data, Hadoop, RHadoop, Decision tree, Naive Bayesian classification, Clustering


Edition: Volume 4 Issue 4, April 2015,


Pages: 2073 - 2076



How to Download this Article?

Type Your Valid Email Address below to Receive the Article PDF Link


Verification Code will appear in 2 Seconds ... Wait

Top