Credit risk assessment method and device

Abstract

The invention discloses a credit risk assessment method and device, and the method comprises the steps: constructing and training a support vector machine, optimizing parameters of the support vectormachine, and generating a classification model; reading a data set and dividing the data set into a plurality of data fragments, and respectively extracting key information and feature vectors with corresponding relations from the plurality of data fragments; performing credit risk assessment on all the feature vectors by using the classification model, and outputting assessment results of all thefeature vectors; and generating a credit evaluation report with a risk coefficient according to the evaluation result, the corresponding key information and the feature vector. Credit evaluation canbe quickly and accurately executed, potential loss of banks is effectively reduced, and loan thresholds of loaners and companies are reduced.

Description

technical field [0001] The present invention relates to the field of risk assessment, more specifically, to a credit risk assessment method and device. Background technique [0002] For banks, the credit of customers directly affects the income of the bank. If a large number of customers default, the bank will face a large amount of bad debt losses. If customers who may default can be identified before lending, it can help banks reduce this part of bad debt losses. Therefore, it is of great significance to evaluate the credit risk of individuals / companies before lending. For credit evaluation agencies and evaluators, credit evaluation indicators are the basis and basis for their credit evaluation work. However, in many credit evaluation systems, there may be problems such as inaccurate evaluation models and too long evaluation time. [0003] There is currently no effective solution to the problems of low accuracy and time-consuming credit evaluation in the prior art. C...

AI Technical Summary

Problems solved by technology

However, in many credit evaluation systems, there may be problems such as inaccurate evaluation models and too long evaluation time

[0003] There is currently no effective solution to the problems of low accuracy and time-consuming credit evaluation in the existing technology

Images