Authors:
Fabio Martinelli
1
;
Francesco Mercaldo
2
;
1
;
Domenico Raucci
3
and
Antonella Santone
2
Affiliations:
1
Institute for Informatics and Telematics, National Research Council of Italy, Pisa, Italy
;
2
Department of Biosciences and Territory, University of Molise, Pesche (IS), Italy
;
3
Department of Economic Studies, G. d’Annunzio University, Chieti-Pescara, Italy
Keyword(s):
Bank Credit Risk Management, Credit Risk Assessment, Probability of Default, Loan Repayment Prediction, Machine Learning, Classification, Association Rules, Data Mining.
Abstract:
In last years, data mining techniques were adopted with the aim to improve and to automatise decision-making processes in a plethora of domains. The banking context, and especially the credit risk management area, can benefit by extracting knowledge from data, for instance by supporting more advanced credit risk assessment approaches. In this study we exploit data mining techniques to estimate the probability of default with regard to loan repayments. We consider supervised machine learning to build predictive models and association rules to infer a set of rules by a real-world data-set, reaching interesting results in terms of accuracy.