Artikel
Explainable AI for credit assessment in banks
Banks' credit scoring models are required by financial authorities to be explainable. This paper proposes an explainable artificial intelligence (XAI) model for predicting credit default on a unique dataset of unsecured consumer loans provided by a Norwegian bank. We combined a LightGBM model with SHAP, which enables the interpretation of explanatory variables affecting the predictions. The LightGBM model clearly outperforms the bank's actual credit scoring model (Logistic Regression). We found that the most important explanatory variables for predicting default in the LightGBM model are the volatility of utilized credit balance, remaining credit in percentage of total credit and the duration of the customer relationship. Our main contribution is the implementation of XAI methods in banking, exploring how these methods can be applied to improve the interpretability and reliability of state-of-the-art AI models. We also suggest a method for analyzing the potential economic value of an improved credit scoring model.
- Sprache
-
Englisch
- Erschienen in
-
Journal: Journal of Risk and Financial Management ; ISSN: 1911-8074 ; Volume: 15 ; Year: 2022 ; Issue: 12 ; Pages: 1-23
- Klassifikation
-
Management
Financial Forecasting and Simulation
Banks; Depository Institutions; Micro Finance Institutions; Mortgages
- Thema
-
credit default prediction
credit risk modelling
explainable artificial intelligence (XAI)
Light Gradient Boosting Machine (LightGBM)
- Ereignis
-
Geistige Schöpfung
- (wer)
-
de Lange, Petter Eilif
Melsom, Borger
Vennerød, Christian Bakke
Westgaard, Sjur
- Ereignis
-
Veröffentlichung
- (wer)
-
MDPI
- (wo)
-
Basel
- (wann)
-
2022
- DOI
-
doi:10.3390/jrfm15120556
- Handle
- Letzte Aktualisierung
-
10.03.2025, 11:45 MEZ
Datenpartner
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Artikel
Beteiligte
- de Lange, Petter Eilif
- Melsom, Borger
- Vennerød, Christian Bakke
- Westgaard, Sjur
- MDPI
Entstanden
- 2022
Ähnliche Objekte (12)
Financial inclusion in emerging economies: The application of machine learning and artificial intelligence in credit risk assessment
Why to buy insurance? An explainable artificial intelligence approach
Credit rating and pricing: Poles apart
Private sector credit and inflation volatility
ESG as a measure of credit ratings
Persistence of bank credit default swap spreads
Advances in credit risk modeling and management
Quantifying correlation uncertainty risk in credit derivatives pricing
What is explainable AI?
Quantity versus price rationing of credit: An empirical test
A system to support the transparency of consumer credit offers
A credit-risk valuation under the variance-gamma asset return
Financial inclusion in emerging economies: The application of machine learning and artificial intelligence in credit risk assessment
Why to buy insurance? An explainable artificial intelligence approach
Credit rating and pricing: Poles apart
Private sector credit and inflation volatility
ESG as a measure of credit ratings
Persistence of bank credit default swap spreads
Advances in credit risk modeling and management
Quantifying correlation uncertainty risk in credit derivatives pricing
What is explainable AI?
Quantity versus price rationing of credit: An empirical test
A system to support the transparency of consumer credit offers
A credit-risk valuation under the variance-gamma asset return
Financial inclusion in emerging economies: The application of machine learning and artificial intelligence in credit risk assessment
Why to buy insurance? An explainable artificial intelligence approach
Credit rating and pricing: Poles apart
Private sector credit and inflation volatility
ESG as a measure of credit ratings
Persistence of bank credit default swap spreads
Advances in credit risk modeling and management
Quantifying correlation uncertainty risk in credit derivatives pricing
What is explainable AI?
Quantity versus price rationing of credit: An empirical test
A system to support the transparency of consumer credit offers