Credit risk prediction method based on knowledge graph and ontology inference engine

Abstract

The invention provides a credit risk prediction method based on a knowledge graph and an ontology inference engine. The credit risk prediction method comprises the following steps: S1, collecting first to nth types of financial information data disclosed by a plurality of loan companies within a set period according to a time sequence; S2, establishing a loan company operation condition knowledge graph; S3, carrying out ontology reasoning on the loan companies, and mining operation state information related to the operation state of the loan companies; S4, establishing a training set and a verification set based on the financial information data and the operation state information of the loan companies, and training a neural network model which is used for predicting the loan risk probability of the loan companies; and S5, collecting financial information data of the loan companies to be subjected to loan risk prediction, mining operation state information of the loan companies, inputting the financial information data and the operation state information of the loan companies into the trained neural network model, and predicting the loan risk probability of the loan companies.

Description

technical field [0001] The invention relates to the technical field of risk control in the financial industry, in particular to a credit risk prediction method based on knowledge graphs and ontology reasoning machines. Background technique [0002] The large scale of my country's bank credit business has brought great strength to the country's economic development and greatly improved the convenience of residents' lives. However, the larger the scale of its development, the higher the requirements for credit risk management. If the effectiveness of risk management cannot be guaranteed, credit will directly affect the stable operation and sustainable and healthy development of commercial banks, and even pose a certain threat to my country's economic development. But the formation of credit risk is a gradual process from germination, accumulation and occurrence. Its symptoms are hidden under the vast financial data information, which is not easy to detect. In the existing t...

AI Technical Summary

Problems solved by technology

However, the accuracy of the neural network early warning credit risk is affected by the transparency of financial data of lending companies

Images