Internet financial gang fraud behavior detection method based on knowledge graph

Abstract

The invention discloses an internet financial gang fraud behavior detection method based on a knowledge graph. The method comprises the following steps: obtaining personal application information, operation behavior burying point data and blacklist data of users of a plurality of preset data sources; preprocessing application information and operation behavior buried point data, segmenting a training set and a test set, marking clients as fraudulent nodes and unmarked nodes according to blacklist hit conditions, solving similarity and affiliation factors between the fraudulent nodes and adjacent user nodes, and performing fraudulent risk assessment on the unmarked nodes to obtain a fraudulent risk assessment result; adopting a Neo4j graph database to construct a knowledge graph, testing averification set fraud risk assessment result, and detecting and processing real-time application user fraud behaviors. According to gang fraud behavior detection of the knowledge graph, the anti-fraud engine is constructed, suspicious group fraud risks are rapidly and efficiently recognized, financial risk control capacity is improved, and credit risks are reduced.

Description

technical field [0001] The invention belongs to the technical field of risk control in the Internet financial industry, and specifically provides a method for detecting fraudulent behavior of Internet financial gangs by using knowledge graphs. Background technique [0002] According to relevant reports, Internet financial institutions lose tens of billions of RMB every year due to fraud risks such as fraudulent personal information, false workplaces, agency packaging, false contacts, and fraudulent loans. Traditional anti-fraud technology mines anti-fraud rules or models from existing historical data, among which supervised algorithms such as logistic regression, decision tree, support vector machine, XGBoost or neural network are the most widely used technologies in current anti-fraud detection Method, this type of method trains a classification model based on historical fraudulent application and normal application data input, outputs fraud probability to quantify fraud ri...

AI Technical Summary

Problems solved by technology

[0003] With the continuous evolution and development of time, the fraud risk model changes rapidly and new fraud methods emerge in an endless stream. In the past, a single individual fraud has rapidly evolved into an organized and large-scale group fraud and the corresponding associated risks. All kinds of forged and false information help customers apply for loans, and sometimes it is not obvious from the perspective of individual fraud characteristics. Traditional anti-fraud methods include identity verification, customer information logic verification, external information comparison verification, blacklist filtering, etc. The method mainly identifies individual risks, and evaluates the risk situation of a single user in isolation. It is impossible to dig out potential group fraud based on the inextricable relationship, and the identification rate of current gang fraud is low.

Images