Show simple item record

dc.creatorGallego, Jorge A. 
dc.creatorRivero, Gonzalo 
dc.creatorMartínez, Juan 
dc.date.accessioned2018-09-26T20:11:03Z
dc.date.available2018-09-26T20:11:03Z
dc.date.created2018-08-20
dc.date.issued2018
dc.identifier.urihttp://repository.urosario.edu.co/handle/10336/18525
dc.descriptionIs it possible to predict corruption and public inefficiency in public procurement? With the proliferation of e-procurement in the public sector, anti-corruption agencies and watchdog organizations in many countries currently have access to powerful sources of information. These may help anticipate which transactions become faulty and why. In this paper, we discuss the promises and challenges of using machine learning models to predict inefficiency and corruption in public procurement, both from the perspective of researchers and practitioners. We exemplify this procedure using a unique dataset characterizing more than 2 million public contracts in Colombia, and training machine learning models to predict which of them face corruption investigations or implementation inefficiencies. We use different techniques to handle the problem of class imbalance typical of these applications, report the high accuracy of our models, simulate the trade-off between precision and recall in this context, and determine which features contribute the most to the prediction of malfeasance within contracts. Our approach is useful for governments interested in exploiting large administrative datasets to improve the provision of public goods and highlights some of the tradeoffs and challenges that they might face throughout this process.
dc.format.extent33
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.relation.urihttps://ideas.repec.org/p/col/000092/016724.html
dc.rightsAtribución-NoComercial-SinDerivadas 2.5 Colombia
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/
dc.subject.ddcAdministración pública 
dc.subject.lembContratos públicos
dc.subject.lembCorrupción política
dc.subject.lembAprendizaje automático (Inteligencia artificial)
dc.titlePreventing rather than Punishing: An Early Warning Model of Malfeasance in Public Procurement
dc.typeworkingPaper
dc.subject.keywordCorruption
dc.subject.keywordInefficiency
dc.subject.keywordMachine Learning
dc.subject.keywordPublic Procurement
dc.rights.accesRightsinfo:eu-repo/semantics/openAccess
dc.type.spaDocumento de trabajo
dc.rights.accesoAbierto (Texto Completo)
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersion
dc.subject.jelC53
dc.subject.jelC55
dc.subject.jelM42
dc.subject.jelO12
dc.contributor.gruplacFacultad de Economía


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Atribución-NoComercial-SinDerivadas 2.5 Colombia
Except where otherwise noted, this item's license is described as Atribución-NoComercial-SinDerivadas 2.5 Colombia

 

Reconocimientos: