Robust fuzzy rule based technique to detect frauds in vehicle insurance
K. S. V. Supraja, S.J. Saritha · 2017
Now-a-days insurance companies have its significance in the society. Customers are interested in claiming the insurance on their property, vehicles. All the vehicle users approach different insurance companies which provide better security to their vehicles. In the same manner the Fraudulent cases also increases. There are different mining techniques in detecting fraud and analyse the data. In this literature survey we present some techniques to fraud analysis, classification and prediction which we consider important to handle fraud detection. Among those The Naïve Bayesian model is more powerful fraud detection in automobile insurance. Bayesian visualization is selected to analyse and interpret the classifier predictions. However this visualization technique is not suitable for abundant data with little frauds. To avoid this limitation, we are using Fuzzy Logic by framing fuzzy rules to improve the Fraud Detection. This technique will be implemented on more number of datasets and variables. By using this technique time complexity will be decreased and implementation is easy and interprets the results accurately.