Credit evaluation method and device based on telephone communication network and social behavior

Abstract

The embodiment of the present invention provides a credit evaluation method and device based on telephone communication network and social behavior, the method includes: obtaining the user's communication information, establishing a communication adjacency matrix according to the communication information; obtaining the communication object in the communication information, and obtaining For the defaulting customers in the communication object, the diffusion energy of the defaulting customer is calculated through the preset diffusion activation model; combined with the adjacency matrix, the risk exposure value of the communication object is calculated through the diffusion energy; the social data of the user is obtained, and the social data and risk exposure The mouth value is input into the preset random forest measurement model as the income feature, and the income data of the income feature is calculated; through the income data, it is judged whether the corresponding user is a default user or a contract user, and the individual income of the corresponding user. By adopting the method, credit evaluation can be carried out on customers based on relevant consumption and social behaviors, which makes the evaluation result more comprehensive and improves the accuracy of credit evaluation.

Description

technical field [0001] The invention relates to the technical field of credit evaluation, in particular to a credit evaluation method and device based on a telephone communication network and social behavior. Background technique [0002] With the increasing popularity of credit loans, people can choose a variety of loan methods to solve the problem of insufficient funds. In the existing loan business, the user's credit is generally evaluated according to the obtained personal information of the user, previous loan records, bank flow and other information, so as to grant loans to the user according to the user's credit and the loan amount applied for by the user. [0003] However, with the advent of the era of big data, this credit evaluation method is not comprehensive enough and not accurate enough. For example, the credit relationship between customers and the customer's own social behavior will also become the "guarantor" of the customer. However, in the existing user c...

AI Technical Summary

Problems solved by technology

[0003] However, with the advent of the era of big data, this credit evaluation method is not comprehensive enough and not accurate enough. For example, the credit relationship between customers and the customer's own social behavior will also become the customer's "guarantor". However, in the existing user credit evaluation methods, the above evaluation factors are not utilized.

Images