Selecting the best measures to discover quantitative association rules

The majority of the existing techniques to mine association rules typically use the support and the confidence to evaluate the quality of the rules obtained. However, these two measures may not be sufficient to properly assess their quality due to some inherent drawbacks they present. A review of th...

Descripción completa

Detalles Bibliográficos
Autores: Martínez Ballesteros, María del Mar, Martínez Álvarez, Francisco, Troncoso Lora, Alicia, Riquelme Santos, José Cristóbal
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2014
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/43558
Acceso en línea:http://hdl.handle.net/11441/43558
https://doi.org/10.1016/j.neucom.2013.01.056
Access Level:acceso abierto
Palabra clave:Quantitative association rules
quality measures
Optimal fitness function
evolutionary algorithms
id ES_92b96a05b8d0270e66cb3aa3ccdbd72f
oai_identifier_str oai:idus.us.es:11441/43558
network_acronym_str ES
network_name_str España
repository_id_str
spelling Selecting the best measures to discover quantitative association rulesMartínez Ballesteros, María del MarMartínez Álvarez, FranciscoTroncoso Lora, AliciaRiquelme Santos, José CristóbalQuantitative association rulesquality measuresOptimal fitness functionevolutionary algorithmsThe majority of the existing techniques to mine association rules typically use the support and the confidence to evaluate the quality of the rules obtained. However, these two measures may not be sufficient to properly assess their quality due to some inherent drawbacks they present. A review of the literature reveals that there exist many measures to evaluate the quality of the rules, but that the simultaneous optimization of all measures is complex and might lead to poor results. In this work, a principal components analysis is applied to a set of measures that evaluate quantitative association rules' quality. From this analysis, a reduced subset of measures has been selected to be included in the fitness function in order to obtain better values for the whole set of quality measures, and not only for those included in the fitness function. This is a general-purpose methodology and can, therefore, be applied to the fitness function of any algorithm. To validate if better results are obtained when using the function fitness composed of the subset of measures proposed here, the existing QARGA algorithm has been applied to a wide variety of datasets. Finally, a comparative analysis of the results obtained by means of the application of QARGA with the original fitness function is provided, showing a remarkable improvement when the new one is used.Ministerio de Ciencia y Tecnología TIN2011-28956-C02ElsevierLenguajes y Sistemas InformáticosMinisterio de Ciencia y Tecnología (MCYT). España2014info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/11441/43558https://doi.org/10.1016/j.neucom.2013.01.056reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésNeurocomputing, 126, 3-14.TIN2011-28956-C02info:eu-repo/semantics/openAccessoai:idus.us.es:11441/435582026-06-17T12:51:07Z
dc.title.none.fl_str_mv Selecting the best measures to discover quantitative association rules
title Selecting the best measures to discover quantitative association rules
spellingShingle Selecting the best measures to discover quantitative association rules
Martínez Ballesteros, María del Mar
Quantitative association rules
quality measures
Optimal fitness function
evolutionary algorithms
title_short Selecting the best measures to discover quantitative association rules
title_full Selecting the best measures to discover quantitative association rules
title_fullStr Selecting the best measures to discover quantitative association rules
title_full_unstemmed Selecting the best measures to discover quantitative association rules
title_sort Selecting the best measures to discover quantitative association rules
dc.creator.none.fl_str_mv Martínez Ballesteros, María del Mar
Martínez Álvarez, Francisco
Troncoso Lora, Alicia
Riquelme Santos, José Cristóbal
author Martínez Ballesteros, María del Mar
author_facet Martínez Ballesteros, María del Mar
Martínez Álvarez, Francisco
Troncoso Lora, Alicia
Riquelme Santos, José Cristóbal
author_role author
author2 Martínez Álvarez, Francisco
Troncoso Lora, Alicia
Riquelme Santos, José Cristóbal
author2_role author
author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
Ministerio de Ciencia y Tecnología (MCYT). España
dc.subject.none.fl_str_mv Quantitative association rules
quality measures
Optimal fitness function
evolutionary algorithms
topic Quantitative association rules
quality measures
Optimal fitness function
evolutionary algorithms
description The majority of the existing techniques to mine association rules typically use the support and the confidence to evaluate the quality of the rules obtained. However, these two measures may not be sufficient to properly assess their quality due to some inherent drawbacks they present. A review of the literature reveals that there exist many measures to evaluate the quality of the rules, but that the simultaneous optimization of all measures is complex and might lead to poor results. In this work, a principal components analysis is applied to a set of measures that evaluate quantitative association rules' quality. From this analysis, a reduced subset of measures has been selected to be included in the fitness function in order to obtain better values for the whole set of quality measures, and not only for those included in the fitness function. This is a general-purpose methodology and can, therefore, be applied to the fitness function of any algorithm. To validate if better results are obtained when using the function fitness composed of the subset of measures proposed here, the existing QARGA algorithm has been applied to a wide variety of datasets. Finally, a comparative analysis of the results obtained by means of the application of QARGA with the original fitness function is provided, showing a remarkable improvement when the new one is used.
publishDate 2014
dc.date.none.fl_str_mv 2014
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11441/43558
https://doi.org/10.1016/j.neucom.2013.01.056
url http://hdl.handle.net/11441/43558
https://doi.org/10.1016/j.neucom.2013.01.056
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Neurocomputing, 126, 3-14.
TIN2011-28956-C02
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 Elsevier
publisher.none.fl_str_mv Elsevier
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_ 1869413493800697856
score 15,301603

Similares en LA Referencia