Credit Card Fraud Prediction System

Abstract

Identity crime is common, and pricey, and credit card fraud is a specific case of identity crime. The existing systems of known fraud matching and business rules have restrictions. To remove these negative aspects in real world, this paper proposes a data mining approach: Communal Detection (CD) and Spike Detection (SD). CD finds real social relationships to reduce the suspicion score, and is impervious to fake social relationships. This approach on a fixed set of attributes is whitelist-oriented. SD increases the suspicion score by finding discrepancies in duplicates. These data mining approaches can detect more types of attacks and removes the unnecessary attributes.