首页>
外国专利>
METHOD FOR DETERMINING CREDIT RATING OPTIMAL WEIGHT VECTOR ON BASIS OF MAXIMUM DEFAULT DISCRIMINATING ABILITY FOR APPROXIMATING AN IDEAL POINT
METHOD FOR DETERMINING CREDIT RATING OPTIMAL WEIGHT VECTOR ON BASIS OF MAXIMUM DEFAULT DISCRIMINATING ABILITY FOR APPROXIMATING AN IDEAL POINT
展开▼
机译:基于理想点最大近似判别能力的信用评级最优权向量确定方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention belongs to the technical field of credit services, and provided thereby is a method for determining credit rating optimal weight vector on the basis of the maximum default discriminating ability for approximating an ideal point. The minimum algebraic sum of the Euclidean distance from the credit score of a non-defaulting enterprise to a positive ideal point and the minimum algebraic sum of the Euclidean distance from the credit score of a defaulting enterprise to a negative ideal point are used as a first objective function. The minimum dispersion degree of "the distance between the score of the non-defaulting enterprise and the positive ideal point" and the minimum dispersion degree of "the distance between the score of the defaulting enterprise and the negative ideal point" are used as a second objective function, and a multi-objective programming function is constructed to reverse a group of optimal weights of a credit rating equation. Ensuring the value of the score of the credit rating equation may significantly distinguish non-defaulting or defaulting clients. The rating result of the credit rating equation is that the score of the non-defaulting enterprise is the highest, while the score of the defaulting enterprise is the lowest. Therefore, the crossover between two types of samples is minimized.
展开▼