Risk identification method and device for transaction data

Abstract

The embodiment of this specification provides a method and device for risk identification of transaction data, wherein the method for risk identification of transaction data includes: acquiring the transaction data of the user's buried point to be identified by adopting the buried point method, and calling the buried point transaction data used in the risk prevention and control application The buried point operation data of at least one risk transaction scene feature group obtained in the way of points; then the buried point transaction data to be identified and the buried point operation data are sequentially sorted according to the order of data generation time to realize the described The combination of the buried point transaction data to be identified and the buried point operation data, and then by inputting the combined buried point transaction data and buried point operation data into the pre-trained risk identification model to identify the buried point Risk identification is performed on the transaction data, and finally, risk prevention and control is performed on the transaction data at the buried point to be identified according to the risk identification result output by the risk identification model.

Description

Risk identification method and device for transaction data technical field [0001] The embodiments of this specification relate to the field of Internet technology, and in particular, to a method for identifying risk of transaction data. One or more embodiments of the present specification also relate to a risk identification device for transaction data, a computing device, to and a computer-readable storage medium. Background technique With the rapid development of information technology, Internet technology has been widely used in the work and life of users. use. For example, more and more users begin to choose to communicate through the Internet and conduct business online through the Internet. and At present, online payment, online transfer, and online transaction are widely used in users' life and work. [0003] At present, in the application program installed on the terminal device, in addition to using payment software for transactions, some real-time Commu...

AI Technical Summary

Problems solved by technology

Although some anti-fraud applications currently exist, the data analysis models of these applications are usually relatively single, and a relatively complete anti-fraud system cannot be formed, and the identification of fraud risks is not accurate and the identification rate is low

And using the traditional database with anti-fraud data to identify the user's transaction data is inefficient and cannot meet the existing requirements

Images