一种信用主体信用评价风险模型的建模方法

• Format: Patent
• Language: Chinese
• Published: 29.03.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

本申请公开了一种信用主体信用评价风险模型的建模方法，针对现有的算法或者模型对信用主体风险预测的结果有可能存在人工干预过大、算法或模型设计缺陷、或者样本数量过少导致的过拟合的现象，通过本说明书中的方法采用技术的手段对其得到的风险预测结果进行处理，以通过对各个风险预测结果的整合，提高对风险预测的精准度。一方面，通过以管理、监督目的的数据处理，得到了对各风险预测结果进行整合后的风险模型。另一方面，得到的风险模型为进一步地减少监督、管理资源的消耗提供了条件。 The invention discloses a modeling method of a credit subject credit evaluation risk model, and aims to solve the problem that an existing algorithm or model may have too large manual intervention on a credit subject risk prediction result, has algorithm or model design defects, or has an overfitting phenomenon caused by too small sample quantity. According to the method provided by the invention, the obtained risk prediction result is processed by adopting a technical means, so that the accuracy of risk prediction is improved by integrating the risk prediction results. On one hand, through data processing for management and supervision purposes, a risk model after integrating various risk prediction results is obtained. And on the other hand, the obtained risk model provides condition