Explainable Credit Risk Scoring in P2P Lending

Ing. Rishee Yadav

Diplomová práce

Anotace:

Credit risk arises when a lender or client in a debt agreement fails to make the required instalment. Major advancements in credit risk intelligence have been made in the last decade to mitigate these risks. Despite that, there are biases toward these models for not being transparent enough. This thesis focuses on the proposed interpretation of models to explain them in-depth and to assess the models’ performance based on comparative analyses to determine their potential and limitations. Not only can these models’ black-box natures be explained, but they can also be used to make some powerful predictions.

Abstract:

Credit risk arises when a lender or client in a debt agreement fails to make the required instalment. Major advancements in credit risk intelligence have been made in the last decade to mitigate these risks. Despite that, there are biases toward these models for not being transparent enough. This thesis focuses on the proposed interpretation of models to explain them in-depth and to assess the models’ performance based on comparative analyses to determine their potential and limitations. Not only can these models’ black-box natures be explained, but they can also be used to make some powerful predictions.

Keywords

Credit risk modelling, credit scoring, black-box, machine learning, peer to peer lending.

Jazyk práce: angličtina

Datum vytvoření / odevzdání či podání práce: 13. 5. 2022

Obhajoba závěrečné práce

• Obhajoba proběhla 22. 6. 2022
• Vedoucí: Ph.D. Oleg Deev
• Oponent: Ing. Tomáš Plíhal, Ph.D.

Masarykova univerzita

Ekonomicko-správní fakulta

Magisterský studijní program / obor:
Finance / Finance