Online transaction multi-subject behavior modeling method based on heterogeneous network representation learning

Abstract

The invention discloses an online transaction multi-subject behavior modeling method based on heterogeneous network representation learning. The modeling method comprises the following steps: step 1,expressing original online transaction data as a heterogeneous network by utilizing an association map, and carrying out data supplement on missing information in the heterogeneous networked transaction data by utilizing heterogeneous network representation learning to establish an individual behavior model; And step 2, establishing behavior models of multiple subjects with different dimensions byutilizing multi-subject behavior modeling, integrating the multiple subject behavior models to obtain a judgment result, and predicting the possibility of transaction abnormity. The method can be used for detecting the fraudulent transaction of the online transaction, intercepting the fraudulent transaction and protecting the fund safety of a user and an enterprise.

Description

technical field [0001] The invention belongs to the technical field of Internet finance, in particular to a multi-subject behavior modeling method for online transactions based on heterogeneous network representation learning Background technique [0002] With the rise of the mobile Internet, various traditional financial services are gradually transferred online. With the rapid development of Internet finance and e-commerce, online transactions on the Internet will bring a large amount of electronic transaction data, and at the same time, the number of online payment fraud transactions will also increase significantly. Attackers complete fraud by stealing user accounts, stealing personal privacy information, and even maliciously attacking servers. In order to ensure the security of users and the company's business, it is necessary to establish an effective network transaction fraud detection system. [0003] At present, the traditional network transaction fraud detection ...

AI Technical Summary

Problems solved by technology

At the same time, some transaction card numbers only have abnormal transaction records or even no historical transaction data. Without normal sample data about transaction card numbers, it is impossible to establish individual-level models for them. How to promote the concept of modeling subjects to achieve different subjects All have sufficient historical data in order to accurately and comprehensively detect the occurrence of fraudulent transactions under different circumstances, which poses challenges to the adaptability and robustness of the model

Images