Credit card anti-fraud prediction method based on dual-mode network diagram mining algorithm

Abstract

The invention discloses a credit card anti-fraud prediction method based on a dual-mode network diagram mining algorithm. The method concretely comprises the following steps that the original data ofthe credit card applicant is acquired and the original data are converted into the diagram data; the nodes, the edges, the attributes of the nodes and the attributes of the edges required for constructing a dual-mode network model are selected out of the diagram data through screening; the dual-mode network model is constructed; a network risk characteristic model is constructed and the probability of network fraud is acquired; the probability of personal fraud is acquired; and the probability of network fraud and the probability of personal fraud are integrated so as to obtain the fraud prediction probability of the credit card applicant. The multidimensional data information related to the applicant is collected, the credit card application field data knowledge map is constructed, the dual-mode network model capable of reflecting the correlation between the clients is acquired and the influence of the individual and group risk on the applicant fraud probability can be accurately integrated so that the risk of identity forgery, group fraud and group attack can be effectively reduced, and the financial anti-fraud risk control capacity can be enhanced.

Description

technical field [0001] The invention relates to the technical field of financial risk control, in particular to a credit card anti-fraud prediction method based on a dual-mode network graph mining algorithm. Background technique [0002] At present, the credit card business has experienced more than 30 years of development in my country, showing a breakthrough growth trend. As of the end of the second quarter of 2016, the number of credit cards and debit cards issued nationwide totaled 473 million, a year-on-year increase of 9.26%. There are 0.31 credit cards, and the total amount of credit card credit is 8.05 trillion yuan, a year-on-year increase of 25.44%. In the current market environment of inclusive finance, traditional finance and Internet technology are constantly merging, and credit card customer acquisition channels are increasingly diversified. Among them, online application is favored by the market due to its fast, convenient and low entry barriers, and has gradua...

AI Technical Summary

Problems solved by technology

[0004] (1) Difficulties in network construction: Online applications usually obtain multiple associations, such as ID number, mobile phone number, device-related, address, unit, etc. What kind of network to build, single-mode network or multi-mode network, how to build The network, how to define the nodes and edges of the network, the fraudulent modes are changing, how to build a network that is dynamically updated in time, and how to use matching technology to establish associations with existing network nodes are all very difficult

[0005] (2) Difficulties in network feature extraction: Different from traditional feature engineering that relies heavily on expert experience, the extraction of network feature engineering requires profound knowledge of graph theory, and different graph indicators are often used according to single-mode or dual-mode networks. How to extract network features based on the constructed network also poses a challenge to risk control modeling experts

[0006] (3) Difficulties in modeling network features: After network feature processing based on graph theory, thousands of dimensional variables are often generated, and usually weak variables with sparse distribution, far exceeding the traditional risk control modeling based on LR (Logistic regression, that is, logic regression) and the range of processing power of the scorecard system

Images