Institutional Repository of Vilnius University
Kredito rizikos reitingavimo modelių skiriamoji geba /
Abstract
dc:descriptionIn the final bachelor's thesis are analysed credit risk rating systems based on logistic regression and linear discriminant analysis. Then discriminatory power tests are performed on their behalf. Also there is analysed a structure of credit risk rating systems, discriminatory power tests are described and used later for model testing, a comparison of rating systems is performed and the efficiency of rating models is summarized based on obtained qualitative assessments. Rating models based on logistic regression and linear discriminant analysis Altman - Z are developed and tested using real historical data of Polish companies in the practical bachelor's thesis part. Both rating systems are compared and evaluated using measures such as the receiver operating characteristic curve (ROC), the area under the curve (AUC), the Pietra index, the Brier score, the χ2 goodness of fit test and the Kendall's τ and Somers'D statistics. Based on the quality measures of these discriminatory power tests, conclusions are drawn on the accuracy of credit risk rating systems in rating potential customers.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Virinaitė, Justė,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD146240249&prefLang=en_US