期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2013
卷号：4
期号：6-4
出版社：Seventh Sense Research Group
摘要：Nowadays the shopping as been evolved as70% online and 30% as offline. In this 30% also 20% have been paid by smart cards. This smart cards usage have found wide spread due to flexible usage. The applications for these credit cards are based on internet or manual applications by the customers who require the smart cards and various loans. The applications in above cases found fraud is a specific case of identity crime. The application fraud pattern is represented by some specific features which may be found duplicates relative to the established base of some criteria. In the existing system we use Communal Detection (CD) i.e. Communal detection Spike Detection (SD) i.e. Spike Detection. Communal Detection (CD) finds real social relationships to reduce the suspicion score and tamper resistant to synthetic social relationships. It is white listoriented approach on a fixed set of attributes. Spike Detection (SD) finds spikes in duplicates to increase the suspicion score, and is proberesistant for attributes. The existing system detects the whether the applicant is fraud. It is the attributeoriented approach on a variablesize set of attributes. In the existing system the fraudster datum nre stored in the database manually. In this proposed system, Communal Detection (CD) and Spike Detection (SD) can detect more types of attacks, better account for varying legal actions, and remove the redundant attributes and to store the fraudulent datum in blacklist using CBR algorithm. CBR algorithm analysis using retrieval, diagnosis and resolution to make the data more secure and to find the fraudulent data. The data that already present or fraudulent is encountered and thrown into the blacklist. Together Communal Detection (CD), Spike Detection (SD) and CBR ensure the data provided by the customer is original. This proposed system makes the system more efficient and enhance the security.
关键词：Communal Detection; Spike Detection; Case Based Reasoning; fraud detection
