Mostrar o rexistro simple do ítem

dc.contributor.authorEiras-Franco, Carlos
dc.contributor.authorGuijarro-Berdiñas, Bertha
dc.contributor.authorAlonso-Betanzos, Amparo
dc.contributor.authorBahamonde, Antonio
dc.date.accessioned2024-04-03T15:21:37Z
dc.date.available2024-04-03T15:21:37Z
dc.date.issued2019-12
dc.identifier.citationEiras-Franco, C., Guijarro-Berdiñas, B., Alonso-Betanzos, A., & Bahamonde, A. (2019). A scalable decision-tree-based method to explain interactions in dyadic data. Decision Support Systems, 127, 113141. https://doi.org/10.1016/j.dss.2019.113141es_ES
dc.identifier.issn0167-9236
dc.identifier.issn1873-5797
dc.identifier.urihttp://hdl.handle.net/2183/36058
dc.descriptionThis version of the article: Eiras-Franco, C., Guijarro-Berdiñas, B., Alonso-Betanzos, A., & Bahamonde, A. (2019). ‘A scalable decision-tree-based method to explain interactions in dyadic data’ has been accepted for publication in: Decision Support Systems, 127, 113141. The Version of Record is available online at https://doi.org/10.1016/j.dss.2019.113141.es_ES
dc.description.abstract[Abstract]: Gaining relevant insight from a dyadic dataset, which describes interactions between two entities, is an open problem that has sparked the interest of researchers and industry data scientists alike. However, the existing methods have poor explainability, a quality that is becoming essential in certain applications. We describe an explainable and scalable method that, operating on dyadic datasets, obtains an easily interpretable high-level summary of the relationship between entities. To do this, we propose a quality measure, which can be configured to a level that suits the user, that factors in the explainability of the model. We report experiments that confirm better results for the proposed method over alternatives, in terms of both explainability and accuracy. We also analyse the method's capacity to extract relevant actionable information and to handle large datasets.es_ES
dc.description.sponsorshipThis research has been supported in part by the Spanish Ministerio de Economía y Competitividad (projects TIN 2015-65069-C2-1-R and 2-R), partially funded by FEDER funds of the EU and by the Xunta de Galicia (projects ED431C 2018/34 and Centro Singular de Investigación de Galicia, accreditation 2016-2019). The authors wish to thank the Fundación Pública Galega Centro Tecnolóxico de Supercomputación de Galicia (CESGA) for the use of their computing resources. We also thank Jorge Díez, Pablo Pérez and Oscar Luaces for providing the data needed to construct the (Outbrain DAY1) dataset and for their assistance in an early stage of this project.es_ES
dc.description.sponsorshipXunta de Galicia; ED431C 2018/34es_ES
dc.language.isoenges_ES
dc.publisherElsevieres_ES
dc.relationinfo:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2015-65069-C2-1-R/ES/ALGORITMOS ESCALABLES DE APRENDIZAJE COMPUTACIONAL: MAS ALLA DE LA CLASIFICACION Y LA REGRESIONes_ES
dc.relationinfo:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2015-65069-C2-2-R/ES/ALGORITMOS ESCALABLES DE APRENDIZAJE COMPUTACIONAL: MAS ALLA DE LA CLASIFICACION Y LA REGRESIONes_ES
dc.relation.urihttps://doi.org/10.1016/j.dss.2019.113141es_ES
dc.rightsAtribución-NoComercial-SinDerivadas 4.0 Internacionales_ES
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subjectDyadic dataes_ES
dc.subjectMachine learninges_ES
dc.subjectInterpretable machine learninges_ES
dc.subjectExplainable artificial intelligencees_ES
dc.subjectScalable machine learninges_ES
dc.titleA scalable decision-tree-based method to explain interactions in dyadic dataes_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.rights.accessinfo:eu-repo/semantics/openAccesses_ES
UDC.journalTitleDecision Support Systemses_ES
UDC.volume127es_ES
UDC.issue113141es_ES
UDC.startPage1es_ES
UDC.endPage10es_ES
dc.identifier.doi10.1016/j.dss.2019.113141


Ficheiros no ítem

Thumbnail
Thumbnail

Este ítem aparece na(s) seguinte(s) colección(s)

Mostrar o rexistro simple do ítem