Documents disponibles écrits par cet auteur

Bound and collapse Bayesian reject inference for credit scoring / G. G. Chen in Journal of the operational research society (JORS), Vol. 63 N° 10 (Octobre 2012) 

Public ISBD [article]  in Journal of the operational research society (JORS) > Vol. 63 N° 10 (Octobre 2012) . - pp. 1374–1387 Titre : Bound and collapse Bayesian reject inference for credit scoring Type de document : texte imprimé Auteurs : G. G. Chen, Auteur ; T. Åstebro, Auteur Année de publication : 2012 Article en page(s) : pp. 1374–1387 Note générale : operational research Langues : Anglais (eng) Mots-clés : statistics;  credit  scoring;  Bayesian;  reject  inference;  missing  data Index. décimale : 001.424 Résumé : Reject inference is a method for inferring how a rejected credit applicant would have behaved had credit been granted. Credit-quality data on rejected applicants are usually missing not at random (MNAR). In order to infer credit-quality data MNAR, we propose a flexible method to generate the probability of missingness within a model-based bound and collapse Bayesian technique. We tested the method's performance relative to traditional reject-inference methods using real data. Results show that our method improves the classification power of credit scoring models under MNAR conditions. Note de contenu : In an earlier version of this article the title was incorrect. The correct title is shown in this final version of the article. Corrected online: 12 January 2012 DEWEY : 001.424 ISSN : 0160-5682 En ligne : http://www.palgrave-journals.com/jors/journal/v63/n10/abs/jors2011149a.html [article] Bound and collapse Bayesian reject inference for credit scoring [texte imprimé] / G. G. Chen, Auteur ; T. Åstebro, Auteur . - 2012 . - pp. 1374–1387. operational research Langues : Anglais (eng) in Journal of the operational research society (JORS) > Vol. 63 N° 10 (Octobre 2012) . - pp. 1374–1387 Mots-clés : statistics;  credit  scoring;  Bayesian;  reject  inference;  missing  data Index. décimale : 001.424 Résumé : Reject inference is a method for inferring how a rejected credit applicant would have behaved had credit been granted. Credit-quality data on rejected applicants are usually missing not at random (MNAR). In order to infer credit-quality data MNAR, we propose a flexible method to generate the probability of missingness within a model-based bound and collapse Bayesian technique. We tested the method's performance relative to traditional reject-inference methods using real data. Results show that our method improves the classification power of credit scoring models under MNAR conditions. Note de contenu : In an earlier version of this article the title was incorrect. The correct title is shown in this final version of the article. Corrected online: 12 January 2012 DEWEY : 001.424 ISSN : 0160-5682 En ligne : http://www.palgrave-journals.com/jors/journal/v63/n10/abs/jors2011149a.html