Gradient Boosting in Motor Insurance Claim Frequency Modelling

Detalhes bibliográficos
Autor(a) principal: Clemente, Carina de Miranda
Data de Publicação: 2023
Outros Autores: Guerreiro, Gracinda Rita Diogo, Bravo, Jorge Miguel
Idioma: eng
Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Texto Completo: http://hdl.handle.net/10362/163312
Resumo: Clemente, C. D. M., Guerreiro, G. R. D., & Bravo, J. M. (2023). Gradient Boosting in Motor Insurance Claim Frequency Modelling. In CAPSI 2023 Proceedings (pp. 53-69). Article 5 (Atas da Conferência da Associação Portuguesa de Sistemas de Informação). Associação Portuguesa de Sistemas de Informação. https://doi.org/10.18803/capsi.v23.53-69 --- This research was funded by national funds through the FCT – Fundação para a Ciência e a Tecnologia, I.P., under the scope of the projects UIDB/00297/2020 and UIDP/00297/2020 -- Center for Mathematics and Applications -- (G. R. Guerreiro) and grants UIDB/04152/2020 - Centro de Investigação em Gestão de Informação (MagIC) and UIDB/00315/2020 -- BRU-ISCTE-IUL -- (J. M. Bravo).
id RCAP_eada25a91e771aadf0377787ac6e88f8
oai_identifier_str oai:run.unl.pt:10362/163312
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Gradient Boosting in Motor Insurance Claim Frequency ModellingGradient BoostingNon-life Insurance PricingExpert systemsPredictive modellingRisk ManagementInformation Systems and ManagementManagement Information SystemsManagement of Technology and InnovationInformation SystemsComputer Science ApplicationsClemente, C. D. M., Guerreiro, G. R. D., & Bravo, J. M. (2023). Gradient Boosting in Motor Insurance Claim Frequency Modelling. In CAPSI 2023 Proceedings (pp. 53-69). Article 5 (Atas da Conferência da Associação Portuguesa de Sistemas de Informação). Associação Portuguesa de Sistemas de Informação. https://doi.org/10.18803/capsi.v23.53-69 --- This research was funded by national funds through the FCT – Fundação para a Ciência e a Tecnologia, I.P., under the scope of the projects UIDB/00297/2020 and UIDP/00297/2020 -- Center for Mathematics and Applications -- (G. R. Guerreiro) and grants UIDB/04152/2020 - Centro de Investigação em Gestão de Informação (MagIC) and UIDB/00315/2020 -- BRU-ISCTE-IUL -- (J. M. Bravo).Modelling claim frequency and claim severity are topics of great interest in property-casualty insurance for supporting underwriting, ratemaking, and reserving actuarial decisions. This paper investigates the predictive performance of Gradient Boosting with Decision Trees as base learners to model the claim frequency in motor insurance using a private cross-country large insurance dataset. The Gradient Boosting algorithm combines many weak base learners to tackle conceptual uncertainty in empirical research. The findings show that the Gradient Boosting model is superior to the standard Generalised Linear Model in the sense that it provides closer predictions in the claim frequency model. The finding also shows that Gradient Boosting can capture the nonlinear relation between the claim counts and feature variables and their complex interactions being, thus, a valuable tool for feature engineering and the development of a data-driven approach to risk management.APSI - Associação Portuguesa de Sistemas de InformaçãoNOVA Information Management School (NOVA IMS)CMA - Centro de Matemática e AplicaçõesFaculdade de Ciências e Tecnologia (FCT)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNClemente, Carina de MirandaGuerreiro, Gracinda Rita DiogoBravo, Jorge Miguel2024-02-09T00:23:07Z2023-10-212023-10-21T00:00:00Zconference objectinfo:eu-repo/semantics/publishedVersion18application/pdfhttp://hdl.handle.net/10362/163312eng2183-489XPURE: 83055137https://doi.org/10.18803/capsi.v23.53-69info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:18:12Zoai:run.unl.pt:10362/163312Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:48:51.321129Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Gradient Boosting in Motor Insurance Claim Frequency Modelling
title Gradient Boosting in Motor Insurance Claim Frequency Modelling
spellingShingle Gradient Boosting in Motor Insurance Claim Frequency Modelling
Clemente, Carina de Miranda
Gradient Boosting
Non-life Insurance Pricing
Expert systems
Predictive modelling
Risk Management
Information Systems and Management
Management Information Systems
Management of Technology and Innovation
Information Systems
Computer Science Applications
title_short Gradient Boosting in Motor Insurance Claim Frequency Modelling
title_full Gradient Boosting in Motor Insurance Claim Frequency Modelling
title_fullStr Gradient Boosting in Motor Insurance Claim Frequency Modelling
title_full_unstemmed Gradient Boosting in Motor Insurance Claim Frequency Modelling
title_sort Gradient Boosting in Motor Insurance Claim Frequency Modelling
author Clemente, Carina de Miranda
author_facet Clemente, Carina de Miranda
Guerreiro, Gracinda Rita Diogo
Bravo, Jorge Miguel
author_role author
author2 Guerreiro, Gracinda Rita Diogo
Bravo, Jorge Miguel
author2_role author
author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
CMA - Centro de Matemática e Aplicações
Faculdade de Ciências e Tecnologia (FCT)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Clemente, Carina de Miranda
Guerreiro, Gracinda Rita Diogo
Bravo, Jorge Miguel
dc.subject.por.fl_str_mv Gradient Boosting
Non-life Insurance Pricing
Expert systems
Predictive modelling
Risk Management
Information Systems and Management
Management Information Systems
Management of Technology and Innovation
Information Systems
Computer Science Applications
topic Gradient Boosting
Non-life Insurance Pricing
Expert systems
Predictive modelling
Risk Management
Information Systems and Management
Management Information Systems
Management of Technology and Innovation
Information Systems
Computer Science Applications
description Clemente, C. D. M., Guerreiro, G. R. D., & Bravo, J. M. (2023). Gradient Boosting in Motor Insurance Claim Frequency Modelling. In CAPSI 2023 Proceedings (pp. 53-69). Article 5 (Atas da Conferência da Associação Portuguesa de Sistemas de Informação). Associação Portuguesa de Sistemas de Informação. https://doi.org/10.18803/capsi.v23.53-69 --- This research was funded by national funds through the FCT – Fundação para a Ciência e a Tecnologia, I.P., under the scope of the projects UIDB/00297/2020 and UIDP/00297/2020 -- Center for Mathematics and Applications -- (G. R. Guerreiro) and grants UIDB/04152/2020 - Centro de Investigação em Gestão de Informação (MagIC) and UIDB/00315/2020 -- BRU-ISCTE-IUL -- (J. M. Bravo).
publishDate 2023
dc.date.none.fl_str_mv 2023-10-21
2023-10-21T00:00:00Z
2024-02-09T00:23:07Z
dc.type.driver.fl_str_mv conference object
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/163312
url http://hdl.handle.net/10362/163312
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2183-489X
PURE: 83055137
https://doi.org/10.18803/capsi.v23.53-69
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 18
application/pdf
dc.publisher.none.fl_str_mv APSI - Associação Portuguesa de Sistemas de Informação
publisher.none.fl_str_mv APSI - Associação Portuguesa de Sistemas de Informação
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596980962525185

Registros relacionados