Skip navigation
Full metadata record
DC FieldValue
dc.contributor.authorAlonso, Andrés
dc.contributor.authorCarbó Martinez, José Manuel
dc.date.accessioned2021-05-24T10:04:30Z
dc.date.available2021-05-24T10:04:30Z
dc.date.issued2021-05-24
dc.identifier.urihttps://repositorio.bde.es/handle/123456789/16694
dc.descriptionSummary of Banco de España Working Paper no. 2105
dc.format.extent3 p.
dc.language.isoeng
dc.publisherBanco de España
dc.relation.ispartofResearch Update / Banco de España, Spring 2021, p. 11-13
dc.relation.hasversionDocumento relacionado 123456789/14691
dc.rightsReconocimiento-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0)
dc.rightsIn Copyright - Non Commercial Use Permitted
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/4.0/deed.es_ES
dc.rights.urihttp://rightsstatements.org/vocab/InC-NC/1.0/
dc.subjectAprendizaje automático
dc.subjectRiesgo de crédito
dc.subjectPredicción
dc.subjectProbabilidad de impago
dc.subjectModelos IRB
dc.subjectMachine learning
dc.subjectCredit risk
dc.subjectPrediction
dc.subjectProbability of default
dc.subjectIRB system
dc.titleUnderstanding the performance of machine learning models to predict credit default: a novel approach for supervisory evaluation
dc.typeArtículo
dc.identifier.bdepubREUP-202105-3
dc.subject.bdeRedes neuronales
dc.subject.bdePredicción
dc.subject.bdeInteligencia artificial
dc.subject.bdeSistemas bancarios y actividad crediticia
dc.publisher.bdeMadrid : Banco de España, 2021
Appears in Collections:


loading