Credit decision-making method, device and equipment based on credit risk control model and medium

Abstract

The invention discloses a credit decision-making method and device based on a credit risk control model, equipment and a medium. The method comprises the steps of acquiring enterprise identificationsof all enterprises and basic data of all the enterprises; constructing a knowledge graph according to the enterprise identifier and the basic data of the enterprise, wherein the knowledge graph comprises the enterprise identifier, the basic data associated with the enterprise identifier and the associated data; receiving an information acquisition request containing a target enterprise identifier,and acquiring an enterprise identifier matched with the target enterprise identifier, and basic data and associated data associated with the matched enterprise identifier from the knowledge graph; inputting the basic data and the associated data obtained from the knowledge graph into a preset credit risk control model, and receiving a credit risk level output by the credit risk control model; andgenerating a credit application result according to the credit risk level. According to the invention, the human input cost in the credit examination and approval process is reduced, the reliabilityand effectiveness of risk assessment are improved, and the credit examination and approval efficiency is improved.

Description

technical field [0001] The present invention relates to the field of business security, in particular to a credit decision-making method, device, equipment and medium based on a credit risk control model. Background technique [0002] At present, for the credit approval of SME-level customers, the staff of financial and lending institutions mainly review the credit applications submitted by SME-level customers. During the review process, the authenticity and accuracy of the data collected using the central bank’s credit information, public business, industrial and commercial data, etc. are difficult to distinguish and need to be further checked, and the data collection and data analysis process is seriously lagging behind; and the data is not perfect , doubtful data, poor timeliness of data and other issues have brought great difficulties to the credit risk assessment of small and medium-sized enterprises. The existing enterprise credit risk control model and model training...

AI Technical Summary

Problems solved by technology

During the review process, the authenticity and accuracy of the data collected using the central bank’s credit information, public business, industrial and commercial data, etc. are difficult to distinguish and need to be further checked, and the data collection and data analysis process is seriously lagging behind; and the data is not perfect , doubtful data, poor timeliness of data and other issues have brought great difficulties to the credit risk assessment of small and medium-sized enterprises

The existing enterprise credit risk control model and model training process are largely limited by the obtained data, and its credit risk assessment and decision-making methods mainly rely on subjective judgments (or expert rules), which leads to the evaluation of existing technologies. The results are not reliable, and the data collection and data analysis process is seriously delayed, making the risk assessment timeliness insufficient

Images