Distance based Model to Detect Healthcare Insurance Fraud within Unsupervised Database

Objectives: Healthcare fraud costs the country tens of billions of dollars a year. Methods: Fraudulent behaviors of healthcare providers and patients have become a serious burden to insurance systems by bringing unnecessary costs. Insurance companies thus developed methods to identify fraud. Results: In this paper a methodology offered based on data mining approach to discover fraud in healthcare insurance. Applications: To test and evaluate model real-world data set related to healthcare insurance in Iran has been used. Investment result of operation model on this data set indicates proper performance of it. Keywords: Anomaly Detection, Data Mining, Healthcare Fraud, Outlier Detection, Unsupervised Method