English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A major requirement for credit scoring models is to provide a maximallyaccurate risk prediction. Additionally, regulators demand these models to betransparent and auditable. Thus, in credit scoring, very simple predictivemodels such as logistic regression or decision trees are still widely used andthe superior predictive power of modern machine learning algorithms cannot befully leveraged. Significant potential is therefore missed, leading to higherreserves or more credit defaults. This paper works out different dimensionsthat have to be considered for making credit scoring models understandable andpresents a framework for making ``black box'' machine learning modelstransparent, auditable and explainable. Following this framework, we present anoverview of techniques, demonstrate how they can be applied in credit scoringand how results compare to the interpretability of score cards. A real worldcase study shows that a comparable degree of interpretability can be achievedwhile machine learning techniques keep their ability to improve predictivepower.

Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoring