Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques

Abstract: In this paper, we propose and compare new methodologies for ranking the importance of variables in productive processes via an adaptation of OneClass Support Vector Machines. In particular, we adapt two methodologies inspired by the machine learning literature: one involving the random shu...

Descripción completa

Detalles Bibliográficos
Autores: Moragues, Raul, Aparicio, Juan, Esteve, Miriam
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universidad Miguel Hernández de Elche
Repositorio:REDIUMH. Depósito Digital de la UMH
OAI Identifier:oai:dspace.umh.es:11000/35050
Acceso en línea:https://hdl.handle.net/11000/35050
Access Level:acceso abierto
Palabra clave:data envelopment analysis
feature ranking
model specification
unsupervised machine learning
technical efficiency
overfitting
CDU::5 - Ciencias puras y naturales::51 - Matemáticas
id ES_e013a0911b6f2ee4e61392aabfb20a7f
oai_identifier_str oai:dspace.umh.es:11000/35050
network_acronym_str ES
network_name_str España
repository_id_str
spelling Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning TechniquesMoragues, RaulAparicio, JuanEsteve, Miriamdata envelopment analysisfeature rankingmodel specificationunsupervised machine learningtechnical efficiencyoverfittingCDU::5 - Ciencias puras y naturales::51 - MatemáticasAbstract: In this paper, we propose and compare new methodologies for ranking the importance of variables in productive processes via an adaptation of OneClass Support Vector Machines. In particular, we adapt two methodologies inspired by the machine learning literature: one involving the random shuffling of values of a variable and another one using the objective value of the dual formulation of the model. Additionally, we motivate the use of these type of algorithms in the production context and compare their performance via a computational experiment. We observe that the methodology based on shuffling the values of a variable outperforms the methodology based on the dual formulation. We observe that the shuffling-based methodology correctly ranks the variables in 94% of the scenarios with one relevant input and one irrelevant input. Moreover, it correctly ranks each variable in at least 65% of replications of a scenario with three relevant inputs and one irrelevant input.MDPIDepartamentos de la UMH::Estadística, Matemáticas e Informática202520252023info:eu-repo/semantics/articleapplication/pdf24application/pdfhttps://hdl.handle.net/11000/35050reponame:REDIUMH. Depósito Digital de la UMHinstname:Universidad Miguel Hernández de ElcheInglés1111https://doi.org/10.3390/math11112590info:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/oai:dspace.umh.es:11000/350502026-05-27T13:36:21Z
dc.title.none.fl_str_mv Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
title Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
spellingShingle Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
Moragues, Raul
data envelopment analysis
feature ranking
model specification
unsupervised machine learning
technical efficiency
overfitting
CDU::5 - Ciencias puras y naturales::51 - Matemáticas
title_short Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
title_full Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
title_fullStr Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
title_full_unstemmed Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
title_sort Ranking the Importance of Variables in a Nonparametric Frontier Analysis Using Unsupervised Machine Learning Techniques
dc.creator.none.fl_str_mv Moragues, Raul
Aparicio, Juan
Esteve, Miriam
author Moragues, Raul
author_facet Moragues, Raul
Aparicio, Juan
Esteve, Miriam
author_role author
author2 Aparicio, Juan
Esteve, Miriam
author2_role author
author
dc.contributor.none.fl_str_mv Departamentos de la UMH::Estadística, Matemáticas e Informática
dc.subject.none.fl_str_mv data envelopment analysis
feature ranking
model specification
unsupervised machine learning
technical efficiency
overfitting
CDU::5 - Ciencias puras y naturales::51 - Matemáticas
topic data envelopment analysis
feature ranking
model specification
unsupervised machine learning
technical efficiency
overfitting
CDU::5 - Ciencias puras y naturales::51 - Matemáticas
description Abstract: In this paper, we propose and compare new methodologies for ranking the importance of variables in productive processes via an adaptation of OneClass Support Vector Machines. In particular, we adapt two methodologies inspired by the machine learning literature: one involving the random shuffling of values of a variable and another one using the objective value of the dual formulation of the model. Additionally, we motivate the use of these type of algorithms in the production context and compare their performance via a computational experiment. We observe that the methodology based on shuffling the values of a variable outperforms the methodology based on the dual formulation. We observe that the shuffling-based methodology correctly ranks the variables in 94% of the scenarios with one relevant input and one irrelevant input. Moreover, it correctly ranks each variable in at least 65% of replications of a scenario with three relevant inputs and one irrelevant input.
publishDate 2023
dc.date.none.fl_str_mv 2023
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/11000/35050
url https://hdl.handle.net/11000/35050
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv 11
11
https://doi.org/10.3390/math11112590
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.format.none.fl_str_mv application/pdf
24
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:REDIUMH. Depósito Digital de la UMH
instname:Universidad Miguel Hernández de Elche
instname_str Universidad Miguel Hernández de Elche
reponame_str REDIUMH. Depósito Digital de la UMH
collection REDIUMH. Depósito Digital de la UMH
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422145663139840
score 15.81155

Similares en LA Referencia