Show simple item record

dc.contributor.authorBenítez-Peña, Sandra
dc.contributor.authorBlanquero, Rafael
dc.contributor.authorCarrizosa, Emilio
dc.contributor.authorRamírez Cobo, Josefa 
dc.contributor.otherEstadística e Investigación Operativaes_ES
dc.date.accessioned2024-06-19T08:36:15Z
dc.date.available2024-06-19T08:36:15Z
dc.date.issued2024
dc.identifier.issn0377-2217
dc.identifier.urihttp://hdl.handle.net/10498/32645
dc.description.abstractSupport vector machines (SVMs) are widely used and constitute one of the best examined and used machine learning models for two-class classification. Classification in SVM is based on a score procedure, yielding a deterministic classification rule, which can be transformed into a probabilistic rule (as implemented in off-the-shelf SVM libraries), but is not probabilistic in nature. On the other hand, the tuning of the regularization parameters in SVM is known to imply a high computational effort and generates pieces of information that are not fully exploited, not being used to build a probabilistic classification rule. In this paper we propose a novel approach to generate probabilistic outputs for the SVM. The new method has the following three properties. First, it is designed to be cost-sensitive, and thus the different importance of sensitivity (or true positive rate, TPR) and specificity (true negative rate, TNR) is readily accommodated in the model. As a result, the model can deal with imbalanced datasets which are common in operational business problems as churn prediction or credit scoring. Second, the SVM is embedded in an ensemble method to improve its performance, making use of the valuable information generated in the parameters tuning process. Finally, the probabilities estimation is done via bootstrap estimates, avoiding the use of parametric models as competing approaches. Numerical tests on a wide range of datasets show the advantages of our approach over benchmark procedures.es_ES
dc.formatapplication/pdfes_ES
dc.language.isoenges_ES
dc.publisherELSEVIERes_ES
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.sourceEuropean Journal of Operational Research, Vol. 314, Núm. 1, 2024, pp. 268-279es_ES
dc.subjectMachine Learninges_ES
dc.subjectSupport Vector Machineses_ES
dc.subjectProbabilistic Classificationes_ES
dc.subjectCost-Sensitive Classificationes_ES
dc.titleCost-sensitive probabilistic predictions for support vector machineses_ES
dc.typejournal articlees_ES
dc.rights.accessRightsopen accesses_ES
dc.identifier.doi10.1016/J.EJOR.2023.09.027
dc.relation.projectIDinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-110886RB-I00/ES/MATHEMATICAL OPTIMIZATION FOR DATA-DRIVEN DEICSION-MAKING/ es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/822214/EU es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/AEI//TED2021-130216A-I00 es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/Universidad de Cádiz/PR2019-029es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/AEI//FJC2021-047209-Ies_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/Junta de Andalucía//US-1381178es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/Junta de Andalucía//P18-FR-2369es_ES
dc.type.hasVersionVoRes_ES


Files in this item

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 Internacional
This work is under a Creative Commons License Attribution-NonCommercial-NoDerivatives 4.0 Internacional