Fraud detection and frequent pattern matching in insurance claims using data mining techniques

Fraudulent insurance claims increase the burden on society. Frauds in health care systems have not only led to additional expenses but also degrade the quality and care which should be provided to patients. Insurance fraud detection is quite subjective in nature and is fettered with societal need. This empirical study aims to identify and gauge the frauds in health insurance data. The contribution of this insurance claim fraud detection experimental study untangle the fraud identification frequent patterns underlying in the insurance claim data using rule based pattern mining. This experiment is an effort to assess the fraudulent patterns in the data on the basis of two criteria-period based claim anomalies and disease based anomalies. Rule based mining results according to both criteria are analysed. Statistical Decision rules and k-means clustering are applied on Period based claim anomalies outliers detection and association rule based mining with Gaussian distribution is applied on disease based anomalies outlier detection. These outliers depict fraud insurance claims in the data. The proposed approach has been evaluated on real-world dataset of a health insurance organization and results show that our proposed approach is efficient in detecting fraud insurance claim using rule based mining.