USING KOHONENS SELF-ORGANIZING FEATURE MAP TO UNCOVER AUTOMOBILE BODILY INJURY CLAIMS FRAUD

Claims fraud is an increasingly vexing problem confronting the insuran ce industry. In this empirical study, we apply Kohonen's Self-Organizi ng Feature Map to classify automobile bodily injury (BT) claims by the degree of fraud suspicion. Feed forward neural networks and a back pr opagation algorithm are used to investigate the validity of the Featur e Map approach. Comparative experiments illustrate the potential usefu lness of the proposed methodology. We show that this technique perform s better than both an insurance adjuster's fraud assessment and an ins urance investigator's fraud assessment with respect to consistency and reliability.