Credit Risk Analysis using Machine and Deep learning models

Peter Martey Addo (), Dominique Guégan () and Bertrand Hassani ()
Additional contact information
Peter Martey Addo: Data Scientist (Lead), Expert Synapses, SNCF Mobilite, http://www.pmaddo.com/
Dominique Guégan: Université Paris1 Panthéon-Sorbonne, Centre d'Economie de la Sorbonne, LabEx ReFi and Ca' Foscari University of Venezia, https://cv.archives-ouvertes.fr/dominique-guegan
Bertrand Hassani: VP, Chief Data Scientist, Capgemini Consulting and LabEx ReFi

Documents de travail du Centre d'Economie de la Sorbonne from Université Panthéon-Sorbonne (Paris 1), Centre d'Economie de la Sorbonne

Abstract: Due to the hyper technology associated to Big Data, data availability and computing power, most banks or lending financial institutions are renewing their business models. Credit risk predictions, monitoring, model reliability and effective loan processing are key to decision making and transparency. In this work, we build binary classifiers based on machine and deep learning models on real data in predicting loan default probability. The top 10 important features from these models are selected and then used in the modelling process to test the stability of binary classifiers by comparing performance on separate data. We observe that tree-based models are more stable than models based on multilayer artificial neural networks. This opens several questions relative to the intensive used of deep learning systems in the enterprises

Keywords: Credit risk; Financial regulation; Data Science; Bigdata; Deep learning (search for similar items in EconPapers)
JEL-codes: C02 C13 C19 D81 G01 G21 G28 G31 (search for similar items in EconPapers)
Pages: 31 pages
Date: 2018-02
New Economics Papers: this item is included in nep-ban, nep-big, nep-cmp and nep-rmg
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (54)

Downloads: (external link)
ftp://mse.univ-paris1.fr/pub/mse/CES2018/18003.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:mse:cesdoc:18003

Access Statistics for this paper

More papers in Documents de travail du Centre d'Economie de la Sorbonne from Université Panthéon-Sorbonne (Paris 1), Centre d'Economie de la Sorbonne Contact information at EDIRC.
Bibliographic data for series maintained by Lucie Label ().