Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison

Credit risk assessment represents a key instrument in the decision-making of the banking and financial institutions. In this article, we present a framework for credit risk strategies to improve portfolio efficiency under a change of macroeconomic regime. The aim is to compare the accuracy of severa...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ana-Maria Sandica, Alexandra Fratila (Adam)
Formato:	article
Lenguaje:	EN
Publicado:	Taylor & Francis Group 2021
Materias:	credit policy financial distress risk aversion boosting random forest Economic growth, development, planning HD72-88 Regional economics. Space in economics HT388
Acceso en línea:	https://doaj.org/article/9e79b3fcb02941e1b70d124658772b7b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9e79b3fcb02941e1b70d124658772b7b
record_format	dspace
spelling	oai:doaj.org-article:9e79b3fcb02941e1b70d124658772b7b2021-11-11T14:23:41ZImplications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison1331-677X1848-966410.1080/1331677X.2021.1997625https://doaj.org/article/9e79b3fcb02941e1b70d124658772b7b2021-10-01T00:00:00Zhttp://dx.doi.org/10.1080/1331677X.2021.1997625https://doaj.org/toc/1331-677Xhttps://doaj.org/toc/1848-9664Credit risk assessment represents a key instrument in the decision-making of the banking and financial institutions. In this article, we present a framework for credit risk strategies to improve portfolio efficiency under a change of macroeconomic regime. The aim is to compare the accuracy of several ensemble methods (AdaBoost, Logit Boost, Gentle Boost and Random Forest) on a default retail Romanian loan portfolio under different risk adversity scenarios, a priori and posteriori the financial distress. Using cost-sensitive ensemble learning models, we concluded that regime-based credit strategy can offer a better alternative in both terms of loss allocated to the strategy as well as defaulters’ classification accuracy.Ana-Maria SandicaAlexandra Fratila (Adam)Taylor & Francis Grouparticlecredit policyfinancial distressrisk aversionboostingrandom forestEconomic growth, development, planningHD72-88Regional economics. Space in economicsHT388ENEkonomska Istraživanja, Vol 0, Iss 0, Pp 1-20 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	credit policy financial distress risk aversion boosting random forest Economic growth, development, planning HD72-88 Regional economics. Space in economics HT388
spellingShingle	credit policy financial distress risk aversion boosting random forest Economic growth, development, planning HD72-88 Regional economics. Space in economics HT388 Ana-Maria Sandica Alexandra Fratila (Adam) Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison
description	Credit risk assessment represents a key instrument in the decision-making of the banking and financial institutions. In this article, we present a framework for credit risk strategies to improve portfolio efficiency under a change of macroeconomic regime. The aim is to compare the accuracy of several ensemble methods (AdaBoost, Logit Boost, Gentle Boost and Random Forest) on a default retail Romanian loan portfolio under different risk adversity scenarios, a priori and posteriori the financial distress. Using cost-sensitive ensemble learning models, we concluded that regime-based credit strategy can offer a better alternative in both terms of loss allocated to the strategy as well as defaulters’ classification accuracy.
format	article
author	Ana-Maria Sandica Alexandra Fratila (Adam)
author_facet	Ana-Maria Sandica Alexandra Fratila (Adam)
author_sort	Ana-Maria Sandica
title	Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison
title_short	Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison
title_full	Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison
title_fullStr	Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison
title_full_unstemmed	Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison
title_sort	implications of macroeconomic conditions on romanian portfolio credit risk. a cost-sensitive ensemble learning methods comparison
publisher	Taylor & Francis Group
publishDate	2021
url	https://doaj.org/article/9e79b3fcb02941e1b70d124658772b7b
work_keys_str_mv	AT anamariasandica implicationsofmacroeconomicconditionsonromanianportfoliocreditriskacostsensitiveensemblelearningmethodscomparison AT alexandrafratilaadam implicationsofmacroeconomicconditionsonromanianportfoliocreditriskacostsensitiveensemblelearningmethodscomparison
_version_	1718438966552690688

Implications of macroeconomic conditions on Romanian portfolio credit risk. A cost-sensitive ensemble learning methods comparison

Ejemplares similares