摘要：The development and application of computational data miningtechniques in nancial fraud detection and business failure prediction hasbecome a popular cross-disciplinary research area in recent times involving nancial economists, forensic accountants and computational modellers.Some of the computational techniques popularly used in the context of -nancial fraud detection and business failure prediction can also be e ectivelyapplied in the detection of fraudulent insurance claims and therefore, can beof immense practical value to the insurance industry. We provide a comparativeanalysis of prediction performance of a battery of data mining techniquesusing real-life automotive insurance fraud data. While the data we have usedin our paper is US-based, the computational techniques we have tested canbe adapted and generally applied to detect similar insurance frauds in othercountries as well where an organized automotive insurance industry exists.
