Credit risk assessment system and method based on weak variable data

Abstract

The invention discloses a credit risk assessment system and method based on weak variable data. The credit risk assessment system comprises an original data platform, a data management platform, a risk control model platform, a small bank score model, a personal qualification assessment module, an address information verification assessment module, an operator information checking assessment module and a payment consumption assessment module. The system depends on a big data intelligent analysis platform and an eagle eye decision engine risk control system independently researched and developed by our company. By combining a big data index real-time calculation function, data modeling and a risk control strategy and cooperating with a plurality of related credit agencies in the industry, the system does not depend on a central bank credit report and strong feature data; the mass weak variable feature data are analzyed, the applicant qualification is reasonably evaluated, the risk is effectively avoided, meanwhile, the client audit passing rate is increased, and the client false killing rate is reduced.

Description

technical field [0001] The invention relates to the technical field related to Internet finance, in particular to a credit risk assessment system and method based on weak variable data. Background technique [0002] At present, with the rapid development of Internet finance, the domestic credit investigation system is not perfect, the effective coverage of the population is small, and personal credit awareness is weak. At the end of November 2017, the central bank's credit investigation covered 950 million people, and about 480 million people had loan records. The coverage rate of the central bank's personal credit investigation was about 50%. In the United States in 2014, this rate was as high as 92%. In China, credit is mostly used in the field of financial credit, while abroad, credit has penetrated into the lives of residents and has become an asset. According to the survey report of Rong 360 "Dimension", more than 10% of users do not care about their personal credit i...

AI Technical Summary

Problems solved by technology

[0003] Domestic banks and financial institutions, especially state-owned banks, have long relied on central bank credit reports and strong variable data in risk control: for example, information such as personal information, income, education, car production, real estate, and personal loan records for risk pricing analysis. However, there are still a large number of people who do not have access to banks

Under the current Internet big data background, there are more and more customers who need financial loans. However, the risk control technology of traditional banks and financial institutions cannot make good use of the Internet big data platform to accurately evaluate the qualifications of applicants, and cannot make good use of Internet big data. The data platform reasonably evaluates the qualifications of applicants, and the main shortcomings are reflected in the following three points:

[0004] 1. The risk control of traditional banks and financial institutions mainly relies on the central bank’s credit report and strong variable characteristic data: for example: personal information, income, education, work, car production, real estate and personal credit records and other information for risk pricing analysis, which cannot be reasonably evaluated Applicant qualification, high customer churn rate;

[0005] 2. The risk control data processing technology of traditional banks and financial institutions is backward, unable to provide real-time calculation of big data indicators, data mining modeling and risk assessment, etc.;

[0006] 3. Traditional banks and financial institutions have huge organizations, and the approval process for risk control technology is lengthy. Once the risk control system is formed, it is difficult to update and iterate online risk control rules in a timely manner according to changes in the external environment to reduce bad debt losses.