نوع مقاله : مقاله علمی - پژوهشی
نویسندگان
1 کارشناس ارشد مدیریت بازرگانی، گرایش مدیریت بیمه، دانشگاه آزاد اسلامی، واحد علوم و تحقیقات تهران (نویسندۀ مسئول)
2 عضو هیات علمی دانشگاه
3 مدیر بیمههای اتومبیل شرکت بیمۀ سینا
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
The insurance industry is prone to fraud due to its nature. In car insurance, the insurer covers all damages brought to third parties by vehicle or vehicle load. In recent years, given the growth of this kind of insurance, it has become necessary to identify the factors influencing decisions that damage be paid for a forgery claim. One way to discover and deal with these sorts of frauds is to investigate the information cited in the cases putting forth the damage claim through third-party insurance. data mining is an appropriate way to interact with these data banks; Also, it may provide valuable knowledge acquired from these databases. In the present study, the attempt is made to explore the fraud patterns in the third-party insurance by investigating up to 142 third-party cases and six variables. The findings indicate that the decision tree and neural net algorithms have better performance in identifying fraudulent, non-fraudulent and suspicious cases than the support vector machine algorithm.
کلیدواژهها [English]