User behavior identification method with transaction character

Abstract

The invention relates to a user behavior recognition method with transaction characters, which establishes a user behavior recognition model with transaction characters from a user transaction behavior reference, a user careful portrait and a distance relationship based on transaction behaviors and careful degrees, thereby realizing behavior recognition. Based on the transaction data and the interaction data, the user is depicted from the perspective of transaction behaviors and transaction characters. According to the method, the fraudulent behavior in the electronic transaction can be effectively detected. From the perspective of practicability, an identification framework is established through transaction behaviors and references, cautious degrees and portraits, a relation model and a risk threshold value, and technical support is provided for solving fraudulent transaction detection.

Description

technical field [0001] The invention relates to the field of information technology, in particular to a method for identifying user behavior with transactional characteristics. Background technique [0002] In recent years, with the mobileization of the global market and the informatization of financial and commodity transactions, the fraud risks exposed in the two major areas of digital finance and e-commerce in the mobile Internet have become more and more serious. The current main forms of mobile fraud include false user fraud, information theft fraud, malicious transaction fraud, financial payment fraud, online fraud, telecommunications fraud, online loan fraud, etc. [0003] User behavior recognition algorithms based on transaction behavior are widely used in the field of electronic transaction fraud detection. In the research on transaction behavior recognition, Bahnsen, A.C., Yu, Xie, Lutao, Zheng, and Kultur, Y. et al. constructed user behavior certificates based on...

AI Technical Summary

Problems solved by technology

However, it has not changed the assessment methods of these traditional psychological theoretical models based on question-and-answer tests, and the use scenarios are still limited

Lack of available personality models, unable to identify users' personalities in real time

[0007] Therefore, due to the limitations of recognition performance caused by ignoring user personality factors and lack of suitable personality models, it is impossible to accurately identify user behaviors, especially when users face new scenarios and occasional behaviors.

Images