Data stream mining based resilient identity fraudulent detection

Abstract

To propose a new safe and secure mechanism to detect identity crimes, more precisely to identify replica in credit card. The synthetic identity fraud is the practice of reliable but false identities which is easy to make but more complicated to apply on real time. Detection system contains two layers which is communal detection and spike detection. Communal detection finds real social relationships to shrink the suspicion score, and is corrupt opposed to synthetic social relationships. It is the white list-oriented approach on a fixed set of attributes. Spike detection finds spikes in duplicates to enhance the suspicion score, and is probe-resistant for attributes. It is the attribute-oriented approach on a variable-size set of attributes. Both communal detection and spike detection become aware of more types of attacks, better account for changing legal behaviour, and remove the redundant attributes. To enhance identity crime detection systems flexible to real world scenario. The response time of the detection and fraud events need to be reduced. In credit card applications the key part is constrained to Identity Crime. Active Phase Blending algorithm is to reduce the time constraints on identifying fraudulent identity usage and response time.