Online transaction fraud detection method based on entity relationship

Abstract

The invention relates to an online transaction fraud detection method based on an entity relationship, which is characterized in that the entity relationship is extracted according to transaction data, a relational network bipartite graph is constructed, and a heterogeneous network homogenization method based on node contraction and a neighborhood information aggregation promotion tree classification model mechanism based on ensemble learning and graph representation learning are provided. According to the method provided by the invention, from the perspective of practicability, the attentionis converted from the transaction node to the multi-order neighborhood information of the transaction in the relational network, and the potential association relationship between the transactions isfully considered, so that the possibility is provided for mining gang fraud. The gradient promotion model improves the fraud identification effect through continuously fitting the residual error of the model, and has a very good performance effect. Meanwhile, the method expands the ensemble learning from the application of the grid-type data to the application field of the graph data. Based on theabove aspects, a framework of the loan transaction fraud detection method is established, and technical support is provided for solving fraud transaction detection.

Description

technical field [0001] The invention relates to a network transaction detection method, which belongs to the field of information technology. Background technique [0002] In recent years, with the development of Internet technology, a large number of new businesses have been spawned in the financial field. While online transactions bring convenience to users, they also provide an opportunity for online black production. The current Internet black industry presents the characteristics of industrialization, precision, mobility, and technology, especially in the field of online credit and financial business, which not only requires the evaluation of the credit qualification of the borrower, but also requires special attention to potential fraudulent behavior. Fighting against online black production has become a core research topic of Internet financial companies. [0003] Analogous to the traditional offline loan process, it is necessary to collect the relationship informat...

AI Technical Summary

Problems solved by technology

However, node2vec is an unsupervised algorithm that does not use the label information of the node itself, and cannot effectively extract feature information for specific classification tasks.

Images