University of Twente Student Theses
Explainable AI in Credit Risk Assessment for External Customers
Matcov, Alexandru (2024) Explainable AI in Credit Risk Assessment for External Customers.
|
PDF
727kB |
| Abstract: | The increasing use of AI in credit risk assessment has brought significant advancements to the financial industry. However, the complex nature of AI models often results in a lack of transparency, making it challenging for customers to understand and trust these systems. This paper will investigate how interpretability methodologies such as LIME and SHAP can improve customer comprehension of AI-driven credit risk evaluations. Through a rigorous literature review and analysis of a public credit dataset, this research will explore effective visualization strategies, evaluate the clarity and transparency that LIME and SHAP offer, and address the challenges of applying these methodologies to enhance interpretability in both public and private datasets. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science, 83 economics |
| Programme: | Business & IT BSc (56066) |
| Link to this item: | https://purl.utwente.nl/essays/98204 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page