A Fuzzy-Based Algorithm for Auditors to Detect Element of Fraud in Settled Insurance Claims

In the current global economy, the survival of insurance companies depends on its ability to respond to the customer demands, which are settlements of the insurance claims. All insurance companies face the conflicting goals of settling claims quickly and authenticating the claims. The increasing cost of human experts in fraud detection has led many companies to develop expert systems, which respond to the needs of the companies in a cost effective and efficient way. It has been observed that the opportunity exists for claim adjustors to settle insurance claims in favor of the claimants simply by colluding with the claimant and sacrificing the monetary interest of the insurers. This use of experts in claim settlement leaves room for subjective judgment and the use of discretion while finalizing a claim. In this paper, we develop a fuzzy logic based expert system that can evaluate and identify the elements of fraud involved in insurance claims settlement. It helps to decide if the claims settled are genuine or their exists an element of fraud which needs substantive testing by an auditor. The proposed methodology has been illustrated with an example that tends to model insurance claims in general. The main contributions of this paper are the 'index of ambiguity' and the fuzzy-logic based methodology to detect an element of fraud in the previously settled insurance claims