Risk assessment method, device and equipment and computer readable storage medium

Abstract

The invention discloses a risk assessment method, device and equipment and a computer readable storage medium, and the method comprises the steps: obtaining the correlation degree between every two entities of various entity types, and obtaining risk tag values corresponding to the entities of various entity types, one entity type being a customer type; and performing at least one round of iterative update calculation by taking the risk label value as an initial risk value to obtain target risk values corresponding to the entities of various entity types, and obtaining a risk value corresponding to the customer according to the target risk values corresponding to the entities of the customer type. Compared with a traditional score card model, the risk assessment scheme does not need to extract risk factors of the customer, and the risk assessment of the customer can be realized only by obtaining the association degree between the entities and the risk label value of each entity.

Description

technical field [0001] The present invention relates to the technical field of risk control, in particular to a risk assessment method, device, equipment and computer-readable storage medium. Background technique [0002] In many application scenarios, it is necessary to conduct risk assessment on customers for risk control. The existing mainstream scheme is based on the idea of ​​the traditional scorecard model: first obtain samples with risky target Y, and extract the risk-related factors X corresponding to the samples, and then perform variable derivation and other algorithm processing on X, and use the supervised algorithm to train the model F , so that the result of F(X) is as consistent as possible with Y, and finally apply F to all customer groups to give a score. However, this traditional scorecard model needs to know the risk factor X of the sample customer. When the risk factor X of the sample customer is missing, the trained model will have poor scoring effect or...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a risk assessment method, device, equipment and computer-readable storage medium, aiming to solve the customer risk assessment method based on the traditional scorecard model, when the risk factor X of the sample customer is missing, it will lead to training The resulting model scores poorly or cannot even be trained to get a technical problem with the model

Images