Identity theft detection method based on probability graph model

Abstract

The invention provides an identity theft detection method based on a probability graph model, which comprises the following steps: S1, collecting, acquiring and preprocessing network payment transaction data to obtain a network payment transaction feature set; S 2, establishing and obtaining a probability graph model by utilizing the network payment transaction feature set; S 3, inputting a training set and training parameters of the probability graph model, and obtaining conditional probability parameters of the probability graph model by utilizing a Bayesian theorem; and S4, predicting an input prediction set by using the conditional probability parameter and the Bayesian theorem to obtain a prediction result. According to the identity theft detection method based on the probability graph model, network payment fraud detection is achieved on the basis of the probability graph model through user synthesis behaviors and attribute modeling, dynamic online adjustment can be conducted onthe detection model, and the accuracy of fraud transaction interception and the robustness of the model are improved.

Description

technical field [0001] The invention relates to the field of anti-fraud detection of Internet financial network payment, in particular to an identity theft detection method based on a probability graph model. Background technique [0002] The mobile Internet is a double-edged sword. While it brings convenience to people's lives, it also brings various hidden dangers. For example, the payment platform for online transactions allows people to shop without leaving home or even anytime, anywhere. And payment, but this convenience and speed also give some unscrupulous attackers an opportunity. Attackers steal users' account information, steal users' personal privacy information, and even pretend to be users themselves to conduct transactions or transfers to complete fraud. Therefore, in order to effectively protect the personal interests of users and companies, it is necessary to establish an effective network payment fraud detection system. [0003] There are already some onlin...

AI Technical Summary

Problems solved by technology

[0003] At present, there are some network payment fraud models based on machine learning or even deep learning. Most of the learning models are discriminant models based on expectation maximization. For online network anti-fraud models, deep learning and other models are used as network payment anti-fraud Although the fraudulent method will be better than other methods in effect, the deep learning model is a typical black box model, and its results are not explanatory and not convincing enough

Images