Credit assessment model training and assessment method and device

Abstract

The invention discloses a credit assessment model training and assessment method and device, and a credit assessment model is obtained through the training method and the training method comprises thesteps of obtaining user data and an assessment result of a user with a correct credit assessment result in a credit investigation system; preprocessing user data in the collected user data, converting the user data into numerical data, including but not limited to performing One hot transform on the category type data, and normalizing the numerical data; constructing m SDT sub-classifiers, m being a positive integer, and constructing an SDT weight generator for generating weight probability distribution of the m SDT sub-classifiers; and performing end-to-end training on the WSDF model with m+ 1 soft decision trees by using the preprocessed user data. The credit assessment model and device constructed by the method has higher working efficiency, and can reduce the bad account rate; and meanwhile, a visual decision-making process is generated.

Description

technical field [0001] The invention discloses a credit evaluation model training and evaluation method and device in the field of financial risk evaluation, and specifically relates to a credit evaluation model training and evaluation method and device based on a weighted soft decision forest. Background technique [0002] Credit assessment is a critical step for financial institutions to predict whether a customer will default. Incorrect credit assessments can cost financial institutions financially. Developing an intelligent credit evaluation system can not only improve the work efficiency of financial institutions, but also reduce the bad debt rate. In recent years, most of the commonly used traditional credit information systems use scorecards to build user credit models. Scorecards are primarily implemented using the logistic regression algorithm, which can improve the performance of linear models. [0003] However, although the commonly used linear model can guaran...

AI Technical Summary

Problems solved by technology

However, due to the complexity of the calculation process, these artificial intelligence algorithms generally have the problem of poor interpretability.

Images