• Login
  • Help Guide
View Item 
  •   JOOUST IR Home
  • Journal Articles
  • School of Biological, Physical, Mathematics & Actuarial Sciences
  • View Item
  •   JOOUST IR Home
  • Journal Articles
  • School of Biological, Physical, Mathematics & Actuarial Sciences
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Performance Evaluation Criteria of Credit Scoring Models for Commercial Lenders

Thumbnail
View/Open
Bakker_Performance Evaluation Criteria of Credit Scoring Models for Commercial Lenders.pdf (318.1Kb)
Publication Date
2019-07
Author
Bakker, Daniel K
Odundo, F
Nyakinda, J
Paul, Samuel F
Type
Article
Metadata
Show full item record
Abstract/Overview

Credit scoring has been regarded as a main tool of different companies or banks during the last few decades and has been widely investigated in different areas, such as finance and accounting. Different scoring techniques are being used in areas of classification and prediction, where statistical techniques have conventionally been used. We used ACC rate, which we believed was an important criterion, especially for new applications of credit scoring, because it highlighted the accuracy of the predictions. Confirmation of these values was done by the AUROC. Different Models were examined and the result showed that using Logistic Regression approach, 19.4% of the applicants were predicted false and 80.6% of them correct, which is relatively high compared to the other models, with the highest sensitivity and the lowest Type II error. That is to say, if we were credit officers, we would conclude that the model at hand, predicts 8 out of 10, the true status of each loan candidate.

Subject/Keywords
Credit Scoring; True Positive Rate; Misclassification Errors
Publisher
International Journal of Mathematics Trends and Technology
ISSN
2231-5373
Permalink
http://ir.jooust.ac.ke:8080/xmlui/handle/123456789/9510
Collections
  • School of Biological, Physical, Mathematics & Actuarial Sciences [254]

Browse

All of JOOUST IRCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister

Statistics

View Usage Statistics

Contact Us

Copyright © 2023-4 Jaramogi Oginga Odinga University of Science and Technology (JOOUST)
P.O. Box 210 - 40601
Bondo – Kenya

Useful Links

  • Report a problem with the content
  • Accessibility Policy
  • Deaccession/Takedown Policy

TwitterFacebookYouTubeInstagram

  • University Policies
  • Access to Information
  • JOOUST Quality Statement