Credit monitoring and scoring method and system based on a behavior model

Abstract

The invention discloses a credit monitoring and scoring method and system based on a behavior model. The method comprises the following steps: obtaining the original data of an account in an observation period; carrying out feature extraction on the original data of the account to obtain a prediction variable; according to the prediction variables, using the machine learning algorithm for modeling, and obtaining the prediction model of the response variables and the prediction variables; predicting an account with repayment performance according to the predicting model to obtain a default probability in the predicting period of the account; calculating the behavior score of the account according to the default probability of the account during the prediction period. The invention can increase the data changing speed, improve the applicability and generalization, and carry out accurate behavior scoring on the account.

Description

technical field [0001] The invention relates to the field of financial credit, in particular to a method and system for monitoring and scoring loans based on a behavior model. Background technique [0002] Credit rating, also known as "credit rating" or reputation evaluation, is an important content and basis for establishing a social credit system. According to the usual definition, credit rating is a credit rating service agency based on a third-party objective and impartial position, based on standardized evaluation indicators system, using scientific evaluation methods and implementing strict evaluation procedures, to assess the credit records, enterprise quality, management ability, operating level, external environment, financial situation, A comprehensive understanding of development prospects, etc., after investigation, research, analysis and research, a comprehensive evaluation of its ability to fulfill its commitments in the future and various risks that may arise,...

AI Technical Summary

Problems solved by technology

[0003] Traditional credit rating methods are mostly based on expert rules or scorecard models, that is, to formulate a set of scoring rules based on expert experience in advance, and then apply this set of rules to perform credit scoring based on the actual data of users. However, this credit rating method is based on historical Scoring based on existing experience has a certain lag and cannot reflect the situation of new users under the new situation, and the designation and modification of the scoring rules need to go through strict expert argumentation, and the cycle of formulation and modification is generally relatively long. Data changes are slow

Images