A fraud detection approach with data mining in health insurance

Kirlidog M., Asuk C.

World Conference on Business, Economics and Management (BEM), Antalya, Turkey, 4 - 06 May 2012, vol.62, pp.989-994, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 62
  • Doi Number: 10.1016/j.sbspro.2012.09.168
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.989-994
  • Keywords: Data mining, health insurance, fraud detection, anomaly detection, support vector machine (SVM)
  • Marmara University Affiliated: Yes

Abstract

Fraud can be seen in all insurance types including health insurance. Fraud in health insurance is done by intentional deception or misrepresentation for gaining some shabby benefit in the form of health expenditures. Data mining tools and techniques can be used to detect fraud in large sets of insurance claim data. Based on a few cases that are known or suspected to be fraudulent, the anomaly detection technique calculates the likelihood or probability of each record to be fraudulent by analyzing the past insurance claims. The analysts can then have a closer investigation for the cases that have been marked by data mining software. (C) 2012 Published by Elsevier Ltd. Selection and/or peer review under responsibility of Prof. Dr. Huseyin Arasli