Maryam Esna-Ashari; Farzan Khamesian; Farbod Khanizadeh
Abstract
Given the significant increase in fraudulent claims and the resulting financial losses, it is important to adopt a scientific approach to detect and prevent such cases. In fact, not equipping companies with an intelligent system to detect suspicious cases has led to the ...
Read More
Given the significant increase in fraudulent claims and the resulting financial losses, it is important to adopt a scientific approach to detect and prevent such cases. In fact, not equipping companies with an intelligent system to detect suspicious cases has led to the payment of such losses, which may in the short term lead to customer happiness but eventually will have negative financial consequences for both insurers and insured. Since data labeled fraud is really limited, this paper, provides insurance companies with an algorithm for identifying suspicious cases. This is obtained with the help of an unsupervised algorithm to detect anomalies in the data set. The use of this algorithm enables insurance companies to detect fraudulent patterns that are difficult to detect even for experienced experts. According to the outcomes, the frequency of financial losses, the time of and the type of incident are the most important factors to in detecting suspicious cases.