Limit model training method and device, limit assessment method and device, equipment and medium

Abstract

The invention discloses a limit model model training method, a limiting assessment method and device, equipment and a medium. The limit model training method comprises the following steps: screening original user data, and obtaining basic user data meeting a training standard, wherein the basic user data comprises a credit line, basic information data, basic asset data and basic consumption data;preprocessing the basic information data to obtain a corresponding life stage category; preprocessing the basic asset data to obtain a repayment capability level corresponding to the basic user data;preprocessing the basic consumption data to obtain a consumption capability level corresponding to the basic user data; marking the credit line, the life stage category, the repayment capability leveland the consumption capability level of the basic user data to obtain training data; training the training data by adopting a GBDT algorithm to obtain a pre-granted credit line model, and solving theproblem that the pre-granted credit line obtained through the pre-granted credit line model is inaccurate.

Description

technical field [0001] The present invention relates to the field of intelligent decision-making, in particular to a quota model training method, quota evaluation method, device, equipment and medium. Background technique [0002] At present, major banks conduct evaluations based on personal information, obtain a pre-credit line (that is, the maximum credit line) and give feedback to users, and users can apply for business based on the pre-credit line. At present, the industry usually evaluates personal information through a pre-credit model to obtain a pre-credit line for users' micro-loan pre-credit lines. Among them, the pre-credit line model is usually modeled based on the basic information of the user and the user's asset situation. However, it is difficult to obtain the asset situation of most users, or the obtained asset situation is relatively one-sided, resulting in low user data integrity. The pre-credit line obtained by the pre-credit line model is not accurate. ...

AI Technical Summary

Problems solved by technology

Among them, the pre-credit line model is usually modeled based on the basic information of the user and the user's asset situation. However, it is difficult to obtain the asset situation of most users, or the obtained asset situation is relatively one-sided, resulting in low user data integrity. The pre-credit limit obtained by the pre-credit limit model is not accurate

Images