Models for inflated data applied to credit risk analysis
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFSCAR |
Texto Completo: | https://repositorio.ufscar.br/handle/ufscar/8631 |
Resumo: | In this thesis, we introduce a methodology based on zero-inflated survival data for the purposes of dealing with propensity to default (credit risk) in bank loan portfolios. Our approach enables us to accommodate three different types of borrowers: (i) individual with event at the starting time, i.e., default on a loan at the beginning; (ii) non-susceptible for the event of default, or (iii) susceptible for the event. The information from borrowers in a given portfolio is exploited through the joint modeling of their survival time, with a multinomial logistic link for the three classes. An advantage of our approach is to accommodate zero-inflated times, which is not possible in the standard cure rate model introduced by Berkson & Gage (1952). The new model proposed is called zero-inflated cure rate model. We also extend the promotion cure rate model studied in Yakovlev & Tsodikov (1996) and Chen et al. (1999), by incorporating excess of zeros in the modelling. Despite allowing to relate covariates to the fraction of cure, the current approach does not enable to relate covariates to the fraction of zeros. The new model proposed is called zero-inflated promotion cure rate model. The second part of this thesis aims at proposing a regression version of the inflated mixture model presented by Calabrese (2014) to deal with multimodality in loss given default data. The novel methodology is applied in four retail portfolios of a large Brazilian commercial bank. |
id |
SCAR_ab82e120377d61c7126f4e3470c5ebf4 |
---|---|
oai_identifier_str |
oai:repositorio.ufscar.br:ufscar/8631 |
network_acronym_str |
SCAR |
network_name_str |
Repositório Institucional da UFSCAR |
repository_id_str |
4322 |
spelling |
Oliveira Júnior, Mauro Ribeiro deLouzada Neto, Franciscohttp://lattes.cnpq.br/0994050156415890http://lattes.cnpq.br/6557207621229352bcbfa7df-6c02-4151-8b70-8353bec2a4902017-04-19T14:13:26Z2017-04-19T14:13:26Z2016-09-27OLIVEIRA JÚNIOR, Mauro Ribeiro de. Models for inflated data applied to credit risk analysis. 2016. Tese (Doutorado em Estatística) – Universidade Federal de São Carlos, São Carlos, 2016. Disponível em: https://repositorio.ufscar.br/handle/ufscar/8631.https://repositorio.ufscar.br/handle/ufscar/8631In this thesis, we introduce a methodology based on zero-inflated survival data for the purposes of dealing with propensity to default (credit risk) in bank loan portfolios. Our approach enables us to accommodate three different types of borrowers: (i) individual with event at the starting time, i.e., default on a loan at the beginning; (ii) non-susceptible for the event of default, or (iii) susceptible for the event. The information from borrowers in a given portfolio is exploited through the joint modeling of their survival time, with a multinomial logistic link for the three classes. An advantage of our approach is to accommodate zero-inflated times, which is not possible in the standard cure rate model introduced by Berkson & Gage (1952). The new model proposed is called zero-inflated cure rate model. We also extend the promotion cure rate model studied in Yakovlev & Tsodikov (1996) and Chen et al. (1999), by incorporating excess of zeros in the modelling. Despite allowing to relate covariates to the fraction of cure, the current approach does not enable to relate covariates to the fraction of zeros. The new model proposed is called zero-inflated promotion cure rate model. The second part of this thesis aims at proposing a regression version of the inflated mixture model presented by Calabrese (2014) to deal with multimodality in loss given default data. The novel methodology is applied in four retail portfolios of a large Brazilian commercial bank.Nesta tese de doutorado, introduzimos uma metodologia baseada em dados de sobrevivência inflacionados em zero com o objetivo de lidar com propensão à inadimplencia (ou seja, risco de crédito) em carteiras de empréstimos bancários. Nossa abordagem permite acomodar (extrair informações de) três tipos diferentes de clientes bancários: (i) indivíduo com empréstimo inadimplente logo no início; (ii) cliente não suscetível ao evento de inadimplência, ou (iii) cliente suscetível ao evento de inadimplir. A informação dos empréstimos em um determinado portfólio é explorada através da modelagem conjunta do seu tempo de sobrevivência, com uma ligação logística multinomial para as três classes. Uma vantagem da nossa abordagem é acomodar tempos inflados em zero, o que não é possível no modelo de fração de cura padrão introduzido por Berkson & Gage (1952). Também estendemos o modelo com fração de cura estudado por Yakovlev & Tsodikov (1996) e Chen et al. (1999), incorporando excesso de zeros na modelagem. Apesar de permitir relacionar covariáveis à fração de cura do modelo, a abordagem padrão não permite relacionar covariáveis com a proporção de zeros dos dados. A segunda parte desta tese visa propor uma versão de regressão do modelo de mistura inflada apresentada por Calabrese (2014), visando extrair informações referentes a multimodalidade apresentada em dados relacionados à perda dado a inadimplência (LGD). A nova metodologia é aplicada em quatro carteiras de empréstimo de varejo de um grande banco comercial brasileiro.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)CAPES: BEX 10583/14-9engUniversidade Federal de São CarlosCâmpus São CarlosPrograma de Pós-Graduação em Estatística - PPGEsUFSCarAnálise de sobrevivênciaModelo misturaModelo tempo promoçãoGestão de risco de créditoCIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICAModels for inflated data applied to credit risk analysisinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisOnline600d0f3b31a-38c4-4c28-aa5b-837ad377108einfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFSCARinstname:Universidade Federal de São Carlos (UFSCAR)instacron:UFSCARORIGINALTeseMROJ.pdfTeseMROJ.pdfapplication/pdf2077202https://repositorio.ufscar.br/bitstream/ufscar/8631/1/TeseMROJ.pdf62fc395e16c6576efb12a5f2918e13d3MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81957https://repositorio.ufscar.br/bitstream/ufscar/8631/2/license.txtae0398b6f8b235e40ad82cba6c50031dMD52TEXTTeseMROJ.pdf.txtTeseMROJ.pdf.txtExtracted texttext/plain206513https://repositorio.ufscar.br/bitstream/ufscar/8631/3/TeseMROJ.pdf.txt0596480ab6375cb2d28024a03b646ec1MD53THUMBNAILTeseMROJ.pdf.jpgTeseMROJ.pdf.jpgIM Thumbnailimage/jpeg6038https://repositorio.ufscar.br/bitstream/ufscar/8631/4/TeseMROJ.pdf.jpg268ff5c098d36bda775d3fe96ce79e0fMD54ufscar/86312023-09-18 18:31:09.669oai:repositorio.ufscar.br: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Repositório InstitucionalPUBhttps://repositorio.ufscar.br/oai/requestopendoar:43222023-09-18T18:31:09Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR)false |
dc.title.eng.fl_str_mv |
Models for inflated data applied to credit risk analysis |
title |
Models for inflated data applied to credit risk analysis |
spellingShingle |
Models for inflated data applied to credit risk analysis Oliveira Júnior, Mauro Ribeiro de Análise de sobrevivência Modelo mistura Modelo tempo promoção Gestão de risco de crédito CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA |
title_short |
Models for inflated data applied to credit risk analysis |
title_full |
Models for inflated data applied to credit risk analysis |
title_fullStr |
Models for inflated data applied to credit risk analysis |
title_full_unstemmed |
Models for inflated data applied to credit risk analysis |
title_sort |
Models for inflated data applied to credit risk analysis |
author |
Oliveira Júnior, Mauro Ribeiro de |
author_facet |
Oliveira Júnior, Mauro Ribeiro de |
author_role |
author |
dc.contributor.authorlattes.por.fl_str_mv |
http://lattes.cnpq.br/6557207621229352 |
dc.contributor.author.fl_str_mv |
Oliveira Júnior, Mauro Ribeiro de |
dc.contributor.advisor1.fl_str_mv |
Louzada Neto, Francisco |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/0994050156415890 |
dc.contributor.authorID.fl_str_mv |
bcbfa7df-6c02-4151-8b70-8353bec2a490 |
contributor_str_mv |
Louzada Neto, Francisco |
dc.subject.por.fl_str_mv |
Análise de sobrevivência Modelo mistura Modelo tempo promoção Gestão de risco de crédito |
topic |
Análise de sobrevivência Modelo mistura Modelo tempo promoção Gestão de risco de crédito CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA |
description |
In this thesis, we introduce a methodology based on zero-inflated survival data for the purposes of dealing with propensity to default (credit risk) in bank loan portfolios. Our approach enables us to accommodate three different types of borrowers: (i) individual with event at the starting time, i.e., default on a loan at the beginning; (ii) non-susceptible for the event of default, or (iii) susceptible for the event. The information from borrowers in a given portfolio is exploited through the joint modeling of their survival time, with a multinomial logistic link for the three classes. An advantage of our approach is to accommodate zero-inflated times, which is not possible in the standard cure rate model introduced by Berkson & Gage (1952). The new model proposed is called zero-inflated cure rate model. We also extend the promotion cure rate model studied in Yakovlev & Tsodikov (1996) and Chen et al. (1999), by incorporating excess of zeros in the modelling. Despite allowing to relate covariates to the fraction of cure, the current approach does not enable to relate covariates to the fraction of zeros. The new model proposed is called zero-inflated promotion cure rate model. The second part of this thesis aims at proposing a regression version of the inflated mixture model presented by Calabrese (2014) to deal with multimodality in loss given default data. The novel methodology is applied in four retail portfolios of a large Brazilian commercial bank. |
publishDate |
2016 |
dc.date.issued.fl_str_mv |
2016-09-27 |
dc.date.accessioned.fl_str_mv |
2017-04-19T14:13:26Z |
dc.date.available.fl_str_mv |
2017-04-19T14:13:26Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
OLIVEIRA JÚNIOR, Mauro Ribeiro de. Models for inflated data applied to credit risk analysis. 2016. Tese (Doutorado em Estatística) – Universidade Federal de São Carlos, São Carlos, 2016. Disponível em: https://repositorio.ufscar.br/handle/ufscar/8631. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufscar.br/handle/ufscar/8631 |
identifier_str_mv |
OLIVEIRA JÚNIOR, Mauro Ribeiro de. Models for inflated data applied to credit risk analysis. 2016. Tese (Doutorado em Estatística) – Universidade Federal de São Carlos, São Carlos, 2016. Disponível em: https://repositorio.ufscar.br/handle/ufscar/8631. |
url |
https://repositorio.ufscar.br/handle/ufscar/8631 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.confidence.fl_str_mv |
600 |
dc.relation.authority.fl_str_mv |
d0f3b31a-38c4-4c28-aa5b-837ad377108e |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus São Carlos |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Estatística - PPGEs |
dc.publisher.initials.fl_str_mv |
UFSCar |
publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus São Carlos |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFSCAR instname:Universidade Federal de São Carlos (UFSCAR) instacron:UFSCAR |
instname_str |
Universidade Federal de São Carlos (UFSCAR) |
instacron_str |
UFSCAR |
institution |
UFSCAR |
reponame_str |
Repositório Institucional da UFSCAR |
collection |
Repositório Institucional da UFSCAR |
bitstream.url.fl_str_mv |
https://repositorio.ufscar.br/bitstream/ufscar/8631/1/TeseMROJ.pdf https://repositorio.ufscar.br/bitstream/ufscar/8631/2/license.txt https://repositorio.ufscar.br/bitstream/ufscar/8631/3/TeseMROJ.pdf.txt https://repositorio.ufscar.br/bitstream/ufscar/8631/4/TeseMROJ.pdf.jpg |
bitstream.checksum.fl_str_mv |
62fc395e16c6576efb12a5f2918e13d3 ae0398b6f8b235e40ad82cba6c50031d 0596480ab6375cb2d28024a03b646ec1 268ff5c098d36bda775d3fe96ce79e0f |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR) |
repository.mail.fl_str_mv |
|
_version_ |
1802136322185363456 |