Automobile Insurance Fraud Detection Using Social Network Analysis
The aim of this paper is detection of organized groups of fraudsters causing more leakage revenue for insurance industry, automobile in particular. Networks play significant roles in representing any relations between entities; thus, they are effective in distinguishing organized fraud activities. We proposed a method by which the groups of perpetrators whose relation form are cycles in the network of accidents.
KeywordsFraud detection Automobile insurance Social network analysis Community detection Fraud cycle detection
- 1.White Paper. (2011). The insurance fraud race: Using information and analytics to stay ahead of criminals. Featuring as an example: SAS® Fraud Framework for Insurance.Google Scholar
- 6.Noble, C. C., & Cook, D. J. (2003). Graph-based anomaly detection. In Proceedings of the ACM SIGKDD international conference on knowledge discovery and datamining (pp. 631–636).Google Scholar
- 8.Maxion, R. A., & Tan, K. M. C. (2000). Benchmarking anomaly-based detection systems. In Proceedings of the international conference on dependable systems and networks (pp. 623–630).Google Scholar
- 11.Cormen, T., Leiserson, C., Rivest, R., & Stein, C. (2002). Introduction to algorithms (2nd ed.p. 1312). Cambridge, MA: The MIT Press ISBN: 9780262033848.Google Scholar