Regulatory learning: How to supervise machine learning models? An application to credit scoring

Regulatory learning: How to supervise machine learning models? An application to credit scoring

The arrival of Big Data strategies is threatening the latest trends in financial regulation related to the simplification of models and the enhancement of the comparability of approaches chosen by financial institutions. Indeed, the intrinsic dynamic philosophy of Big Data strategies is almost incom...

Full description

Bibliographic Details
Main Authors: Dominique Guégan, Bertrand Hassani
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2018-09-01
Series:Journal of Finance and Data Science
Online Access:http://www.sciencedirect.com/science/article/pii/S2405918817300648
id doaj-1bf5bba07fc64e34846e712acc40b1b4
record_format Article
spelling doaj-1bf5bba07fc64e34846e712acc40b1b42021-04-02T10:17:52ZengKeAi Communications Co., Ltd.Journal of Finance and Data Science2405-91882018-09-0143157171Regulatory learning: How to supervise machine learning models? An application to credit scoringDominique Guégan0Bertrand Hassani1Université Paris 1 Panthéon-Sorbonne, IPAG, University Ca'Foscari Venezia and labEx ReFi, CES106 bd de l'Hôpital, 75013 Paris, FranceGroup Capgemini, LabEx ReFi, Université Paris 1 Panthéon-Sorbonne, CES106 bd de l'Hôpital, 75013 Paris, France; University College London Computer Science, 66–72 Gower Street, London WC1E 6EA, UK; Corresponding author. Group Capgemini, LabEx ReFi, Université Paris 1 Panthéon-Sorbonne, CES106 bd de l'Hôpital, 75013 Paris, France.The arrival of Big Data strategies is threatening the latest trends in financial regulation related to the simplification of models and the enhancement of the comparability of approaches chosen by financial institutions. Indeed, the intrinsic dynamic philosophy of Big Data strategies is almost incompatible with the current legal and regulatory framework as illustrated in this paper. Besides, as presented in our application to credit scoring, the model selection may also evolve dynamically forcing both practitioners and regulators to develop libraries of models, strategies allowing to switch from one to the other as well as supervising approaches allowing financial institutions to innovate in a risk mitigated environment. The purpose of this paper is therefore to analyse the issues related to the Big Data environment and in particular to machine learning models highlighting the issues present in the current framework confronting the data flows, the model selection process and the necessity to generate appropriate outcomes. Keywords: Data science, Credit scoring, Machine learning, AUC, Regulationhttp://www.sciencedirect.com/science/article/pii/S2405918817300648
collection DOAJ
language English
format Article
sources DOAJ
author Dominique Guégan
Bertrand Hassani
spellingShingle Dominique Guégan
Bertrand Hassani
Regulatory learning: How to supervise machine learning models? An application to credit scoring
Journal of Finance and Data Science
author_facet Dominique Guégan
Bertrand Hassani
author_sort Dominique Guégan
title Regulatory learning: How to supervise machine learning models? An application to credit scoring
title_short Regulatory learning: How to supervise machine learning models? An application to credit scoring
title_full Regulatory learning: How to supervise machine learning models? An application to credit scoring
title_fullStr Regulatory learning: How to supervise machine learning models? An application to credit scoring
title_full_unstemmed Regulatory learning: How to supervise machine learning models? An application to credit scoring
title_sort regulatory learning: how to supervise machine learning models? an application to credit scoring
publisher KeAi Communications Co., Ltd.
series Journal of Finance and Data Science
issn 2405-9188
publishDate 2018-09-01
description The arrival of Big Data strategies is threatening the latest trends in financial regulation related to the simplification of models and the enhancement of the comparability of approaches chosen by financial institutions. Indeed, the intrinsic dynamic philosophy of Big Data strategies is almost incompatible with the current legal and regulatory framework as illustrated in this paper. Besides, as presented in our application to credit scoring, the model selection may also evolve dynamically forcing both practitioners and regulators to develop libraries of models, strategies allowing to switch from one to the other as well as supervising approaches allowing financial institutions to innovate in a risk mitigated environment. The purpose of this paper is therefore to analyse the issues related to the Big Data environment and in particular to machine learning models highlighting the issues present in the current framework confronting the data flows, the model selection process and the necessity to generate appropriate outcomes. Keywords: Data science, Credit scoring, Machine learning, AUC, Regulation
url http://www.sciencedirect.com/science/article/pii/S2405918817300648
work_keys_str_mv AT dominiqueguegan regulatorylearninghowtosupervisemachinelearningmodelsanapplicationtocreditscoring
AT bertrandhassani regulatorylearninghowtosupervisemachinelearningmodelsanapplicationtocreditscoring
_version_ 1724167564331843584

Similar Items