Show simple item record

Quantification-oriented learning based on reliable classifiers

dc.contributor.authorBarranquero Tolosa, José 
dc.contributor.authorDíez Peláez, Jorge 
dc.contributor.authorCoz Velasco, Juan José del
dc.identifier.citationPattern Recognition, 48(2), p. 591–604 (2015); doi:10.1016/j.patcog.2014.07.032
dc.description.abstractReal-world applications demand effective methods to estimate the class distribution of a sample. In many domains, this is more productive than seeking individual predictions. At a first glance, the straightforward conclusion could be that this task, recently identified as quantification, is as simple as counting the predictions of a classifier. However, due to natural distribution changes occurring in realworld problems, this solution is unsatisfactory. Moreover, current quantification models based on classifiers present the drawback of being trained with loss functions aimed at classification rather than quantification. Other recent attempts to address this issue suffer certain limitations regarding reliability, measured in terms of classification abilities. This paper presents a learning method that optimizes an alternative metric that combines simultaneously quantification and classification performance. Our proposal offers a new framework that allows the construction of binary quantifiers that are able to accurately estimate the proportion of positives, based on models with reliable classification abilities
dc.description.sponsorshipThis work was supported in part by the Spanish Ministerio de Economía y Competitividad, under research project TIN2011-23558. The contribution of Jose Barranquero was also supported by FPI grant BES-2009-027102
dc.format.extentp. 591-604spa
dc.relation.ispartofPattern Recognition, 48(2)spa
dc.rights© 2015 Elsevier
dc.rightsCC Reconocimiento - No comercial - Sin obras derivadas 4.0 Internacional
dc.subjectClass distribution estimation
dc.subjectPerformance metrics
dc.titleQuantification-oriented learning based on reliable classifiersspa
dc.typejournal article
dc.rights.accessRightsopen access

Files in this item


This item appears in the following Collection(s)

Show simple item record

© 2015 Elsevier
This item is protected with a Creative Commons License