Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending

Peer-to-peer (P2P) lending demands effective and explainable credit risk models. Typical machine learning algorithms offer high prediction performance, but most of them lack explanatory power. However, this deficiency can be solved with the help of the explainability tools proposed in the last few y...

Descripción completa

Detalles Bibliográficos
Autores: Ariza Garzón, Miller Janny, Arroyo Gallardo, Javier, Caparrini López, Antonio, Segovia Vargas, María Jesús
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:inglés
OAI Identifier:oai:docta.ucm.es:20.500.14352/92059
Acceso en línea:https://hdl.handle.net/20.500.14352/92059
Access Level:acceso abierto
Palabra clave:Credit risk
P2P lending
Explainability
Shapley values
Boosting
Logistic regression
Ciencias Sociales
53 Ciencias Económicas
id ES_4a2a789d905cdafaab5eaab2eb6b913d
oai_identifier_str oai:docta.ucm.es:20.500.14352/92059
network_acronym_str ES
network_name_str España
repository_id_str
spelling Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer LendingAriza Garzón, Miller JannyArroyo Gallardo, JavierCaparrini López, AntonioSegovia Vargas, María JesúsCredit riskP2P lendingExplainabilityShapley valuesBoostingLogistic regressionCiencias Sociales53 Ciencias EconómicasPeer-to-peer (P2P) lending demands effective and explainable credit risk models. Typical machine learning algorithms offer high prediction performance, but most of them lack explanatory power. However, this deficiency can be solved with the help of the explainability tools proposed in the last few years, such as the SHAP values. In this work, we assess the well-known logistic regression model and several machine learning algorithms for granting scoring in P2P lending. The comparison reveals that the machine learning alternative is superior in terms of not only classification performance but also explainability. More precisely, the SHAP values reveal that machine learning algorithms can reflect dispersion, nonlinearity and structural breaks in the relationships between each feature and the target variable. Our results demonstrate that is possible to have machine learning credit scoring models be both accurate and transparent. Such models provide the trust that the industry, regulators and end-users demand in P2P lending and may lead to a wider adoption of machine learning in this and other risk assessment applications where explainability is required.IEEEUniversidad Complutense de Madrid20202020-01-0120202020-01-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/20.500.14352/92059reponame:Docta Complutenseinstname:Universidad Complutense de Madrid (UCM)InglésengEuropean Commission http://dx.doi.org/10.13039/501100000780 Horizon 2020 Framework Programme 825215open accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:docta.ucm.es:20.500.14352/920592026-06-02T12:44:21Z
dc.title.none.fl_str_mv Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
title Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
spellingShingle Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
Ariza Garzón, Miller Janny
Credit risk
P2P lending
Explainability
Shapley values
Boosting
Logistic regression
Ciencias Sociales
53 Ciencias Económicas
title_short Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
title_full Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
title_fullStr Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
title_full_unstemmed Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
title_sort Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
dc.creator.none.fl_str_mv Ariza Garzón, Miller Janny
Arroyo Gallardo, Javier
Caparrini López, Antonio
Segovia Vargas, María Jesús
author Ariza Garzón, Miller Janny
author_facet Ariza Garzón, Miller Janny
Arroyo Gallardo, Javier
Caparrini López, Antonio
Segovia Vargas, María Jesús
author_role author
author2 Arroyo Gallardo, Javier
Caparrini López, Antonio
Segovia Vargas, María Jesús
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidad Complutense de Madrid
dc.subject.none.fl_str_mv Credit risk
P2P lending
Explainability
Shapley values
Boosting
Logistic regression
Ciencias Sociales
53 Ciencias Económicas
topic Credit risk
P2P lending
Explainability
Shapley values
Boosting
Logistic regression
Ciencias Sociales
53 Ciencias Económicas
description Peer-to-peer (P2P) lending demands effective and explainable credit risk models. Typical machine learning algorithms offer high prediction performance, but most of them lack explanatory power. However, this deficiency can be solved with the help of the explainability tools proposed in the last few years, such as the SHAP values. In this work, we assess the well-known logistic regression model and several machine learning algorithms for granting scoring in P2P lending. The comparison reveals that the machine learning alternative is superior in terms of not only classification performance but also explainability. More precisely, the SHAP values reveal that machine learning algorithms can reflect dispersion, nonlinearity and structural breaks in the relationships between each feature and the target variable. Our results demonstrate that is possible to have machine learning credit scoring models be both accurate and transparent. Such models provide the trust that the industry, regulators and end-users demand in P2P lending and may lead to a wider adoption of machine learning in this and other risk assessment applications where explainability is required.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-01-01
2020
2020-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14352/92059
url https://hdl.handle.net/20.500.14352/92059
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://dx.doi.org/10.13039/501100000780 Horizon 2020 Framework Programme 825215
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Docta Complutense
instname:Universidad Complutense de Madrid (UCM)
instname_str Universidad Complutense de Madrid (UCM)
reponame_str Docta Complutense
collection Docta Complutense
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407468719702016
score 15,300719

Similares en LA Referencia