Facebook Pixel

Application of AI in Credit Scoring Modeling

ISBN:
978-3-658-40179-5
Auflage:
1st ed. 2022
Verlag:
Springer Fachmedien Wiesbaden GmbH
Land des Verlags:
Deutschland
Erscheinungsdatum:
08.12.2022
Autoren:
Reihe:
BestMasters
Format:
Softcover
Seitenanzahl:
83
Ladenpreis
109,99 EUR (inkl. MwSt. zzgl. Versand)
Lieferung in 5-10 Werktagen Versandkostenfrei ab 40 Euro in Österreich
Hinweis: Da dieses Werk nicht aus Österreich stammt, ist es wahrscheinlich, dass es nicht die österreichische Rechtslage enthält. Bitte berücksichtigen Sie dies bei ihrem Kauf.
The scope of this study is to investigate the capability of AI methods to accurately detect and predict credit risks based on retail borrowers' features. The comparison of logistic regression, decision tree, and random forest showed that machine learning methods are able to predict credit defaults of individuals more accurately than the logit model. Furthermore, it was demonstrated how random forest and decision tree models were more sensitive in detecting default borrowers.
Schlagwörter
Biografische Anmerkung
MA Bohdan Popovych is a data scientist and a researcher in quantitative finance. The main scientific focus of the author is application of advanced analytics and artificial intelligence in finance and economics.