Credit fraud detection method and model training method, device and server thereof

Abstract

The invention provides a credit fraud detection method, a training method and device of a credit fraud detection model and a server, and the method comprises the steps: determining a client statistical feature vector and a client relation map through the obtained credit client data; Converting the node sequence in the customer relationship map into a node label sequence through the obtained statelabel data corresponding to the credit customer data; using the skip- gram algorithm to convert the node tag sequence into a feature vector corresponding to the customer relationship map; And according to the statistical feature vector and the feature vector of the customer relationship map, training the initial model until the number of iterations of the training meets a preset iteration number threshold, and obtaining a credit fraud detection model. According to the credit fraud detection model obtained by the invention, the relation graph network structure, the label characteristics and thestatistical characteristic vectors are utilized, so that the fraud risk of a client can be better identified, and the reliability of a risk detection result is improved.

Description

technical field [0001] The present invention relates to the technical field of Internet credit risk control, in particular to a credit fraud detection method and a training method, device and server for its model. Background technique [0002] With the development of knowledge graph and social network technology and its wide application in the Internet field, many Internet financial institutions have also begun to apply relationship graphs to the Internet credit field; for example, visual display of character relationships to assist manual pre-loan approval; Artificially summarize several derived variables from the map based on expert experience, such as first-degree correlation features, second-degree correlation features, etc., or extract such things as out-degree, in-degree, centrality, and PageRank (page level) from social networks based on graph theory features for application scoring or anti-fraud; these methods are based on the network structure of the relationship gr...

AI Technical Summary

Problems solved by technology

[0002] With the development of knowledge graph and social network technology and its wide application in the Internet field, many Internet financial institutions have also begun to apply relationship graphs to the Internet credit field; for example, visual display of character relationships to assist manual pre-loan approval; Artificially summarize several derived variables from the map based on expert experience, such as first-degree correlation features, second-degree correlation features, etc., or extract such things as out-degree, in-degree, centrality, and PageRank (page level) from social networks based on graph theory features for application scoring or anti-fraud; these methods are based on the network structure of the relationship graph to extract certain information features. When faced with a large number of complex networks, there must be certain information missing in this process, and it cannot Fully express the structural information of the network, resulting in Internet credit detection only by the network structure of the relationship graph, and the reliability of the obtained results is poor

Images