Fraud detection using outlier predictor in health insurance data

Abstract

In day today life, health insurance data collection plays major role for employers. In several countries misbehavior in health insurance is a major problem. Health insurance data fraud is an intentional act of misleading, hiding or misrepresenting information that makes profit to a single or group of members. These kind of violation leads to major loss for health insurance providing organisation. Hence Detecting fraudulent and abusive cases in health insurance is one of the most challenging problems. The aim of the project is fraud detection in health insurance data. In order to increase the accuracy of the framework, several methods are utilized, such as the pairwise comparison method of analytic hierarchical processing (AHP). Its mainly focus on a concrete problem of probabilistic outlier detection. Overcoming the existing drawback of time consuming, proactive and retrospective analysis are integrated together, which significantly reduces the time requirements for the fact-finding process.