Mathematical optimization in classification and regression trees

Classification and regression trees, as well as their variants, are off-the-shelf methods in Machine Learning. In this paper, we review recent contributions within the Continuous Optimization and the Mixed-Integer Linear Optimization paradigms to develop novel formulations in this research area. We...

Descripción completa

Detalles Bibliográficos
Autores: Carrizosa Priego, Emilio José, Molero del Río, María Cristina, Romero Morales, Dolores
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/182797
Acceso en línea:https://hdl.handle.net/11441/182797
https://doi.org/10.1007/s11750-021-00594-1
Access Level:acceso abierto
Palabra clave:Classification and regression trees
Tree ensembles
Mixed-integer linear optimization
Continuous nonlinear optimization
Sparsity
Explainability
id ES_330c5361cecd0003e005a989a36a4303
oai_identifier_str oai:idus.us.es:11441/182797
network_acronym_str ES
network_name_str España
repository_id_str
spelling Mathematical optimization in classification and regression treesCarrizosa Priego, Emilio JoséMolero del Río, María CristinaRomero Morales, DoloresClassification and regression treesTree ensemblesMixed-integer linear optimizationContinuous nonlinear optimizationSparsityExplainabilityClassification and regression trees, as well as their variants, are off-the-shelf methods in Machine Learning. In this paper, we review recent contributions within the Continuous Optimization and the Mixed-Integer Linear Optimization paradigms to develop novel formulations in this research area. We compare those in terms of the nature of the decision variables and the constraints required, as well as the optimization algorithms proposed. We illustrate how these powerful formulations enhance the flexibility of tree models, being better suited to incorporate desirable properties such as cost-sensitivity, explainability, and fairness, and to deal with complex data, such as functional data.SpringerEstadística e Investigación OperativaFQM329: Optimización2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/182797https://doi.org/10.1007/s11750-021-00594-1reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésTOP, 29, 5-33.10.1007/s11750-021-00594-1info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1827972026-06-17T12:51:07Z
dc.title.none.fl_str_mv Mathematical optimization in classification and regression trees
title Mathematical optimization in classification and regression trees
spellingShingle Mathematical optimization in classification and regression trees
Carrizosa Priego, Emilio José
Classification and regression trees
Tree ensembles
Mixed-integer linear optimization
Continuous nonlinear optimization
Sparsity
Explainability
title_short Mathematical optimization in classification and regression trees
title_full Mathematical optimization in classification and regression trees
title_fullStr Mathematical optimization in classification and regression trees
title_full_unstemmed Mathematical optimization in classification and regression trees
title_sort Mathematical optimization in classification and regression trees
dc.creator.none.fl_str_mv Carrizosa Priego, Emilio José
Molero del Río, María Cristina
Romero Morales, Dolores
author Carrizosa Priego, Emilio José
author_facet Carrizosa Priego, Emilio José
Molero del Río, María Cristina
Romero Morales, Dolores
author_role author
author2 Molero del Río, María Cristina
Romero Morales, Dolores
author2_role author
author
dc.contributor.none.fl_str_mv Estadística e Investigación Operativa
FQM329: Optimización
dc.subject.none.fl_str_mv Classification and regression trees
Tree ensembles
Mixed-integer linear optimization
Continuous nonlinear optimization
Sparsity
Explainability
topic Classification and regression trees
Tree ensembles
Mixed-integer linear optimization
Continuous nonlinear optimization
Sparsity
Explainability
description Classification and regression trees, as well as their variants, are off-the-shelf methods in Machine Learning. In this paper, we review recent contributions within the Continuous Optimization and the Mixed-Integer Linear Optimization paradigms to develop novel formulations in this research area. We compare those in terms of the nature of the decision variables and the constraints required, as well as the optimization algorithms proposed. We illustrate how these powerful formulations enhance the flexibility of tree models, being better suited to incorporate desirable properties such as cost-sensitivity, explainability, and fairness, and to deal with complex data, such as functional data.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/182797
https://doi.org/10.1007/s11750-021-00594-1
url https://hdl.handle.net/11441/182797
https://doi.org/10.1007/s11750-021-00594-1
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv TOP, 29, 5-33.
10.1007/s11750-021-00594-1
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405721718685696
score 15,81155

Similares en LA Referencia