On the confusion matrix in credit scoring and its analytical properties

被引：71

作者：

Zeng, Guoping ^{[1
]}

机构：

[1] 4522 Oak Shores Dr, Plano, TX 75024 USA

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 2020年 / 49卷 / 09期

关键词：

confusion matrix; sensitivity; specificity; ROC; KS; false positive; false negative; true positive; true negative;

D O I：

10.1080/03610926.2019.1568485

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Confusion Matrix is an important measure to evaluate the accuracy of credit scoring models. However, the literature about Confusion Matrix is limited. The analytical properties of Confusion Matrix are ignored. Moreover, the concept of Confusion Matrix is confusing. In this article, we systematically study Confusion Matrix and its analytical properties. We enumerate 16 possible variants of Confusion Matrix and show that only 8 are reasonable. We study the relationship between Confusion Matrix and 2 other performance measures: the receiver operating characteristic curve (ROC) and Kolmogorov-Smirnov statistic (KS). We show that an optimal cutoff score can be attained by KS.

引用

页码：2080 / 2093

页数：14

共 17 条

[1] [Anonymous], 2015, MACHINE LEARNING R L
[2] Huang J., 2014, THESIS
[3] Kohavi R., 1998, Editorial for the Special Issue on Applications of Machine Learning and the Knowledge Discovery Process
[4] Louzada Francisco, 2016, Surveys in Operations Research and Management Science, V21, P117, DOI 10.1016/j.sorms.2016.10.001
[5] Mailund T., 2017, BEGINNING DATA SCI R, DOI [10.1007/978-1-4842-2671-1, DOI 10.1007/978-1-4842-2671-1]
[6] Refaat M., 2011, Credit Risk Scorecards: Development and Implementation Using SAS
[7] Siddiqi N., 2006, Credit Risk Scorecards - Developing and Implementing Intelligent Credit Scoring
[8] Thomas L., 2017, Credit Scoring and Its Applications
[9] Thomas LC, 2009, CONSUMER CREDIT MODE
[10] Zeng G., 2014, MATH FINANCE LETT, V2014, P1

← 1 2 →