Credit scoring models with truncated samples and their validation

Working papers | 2006 | N 4

Authors

  • Verónica Balzarotti Banco Central de la República Argentina
  • Matías Gutiérrez Girault Banco Central de la República Argentina
  • Verónica Vallés Banco Central de la República Argentina

Keywords:

Credit scoring models, Debtors Central

Abstract

The main objective of this work is to develop a credit scoring methodology for commercial bank debtors in Argentina, based on information available in the Central Debtors ("CD") as a reference tool to evaluate credit risk in local banks. Previous experience in this field has shown promising results. In this work we focus on two innovative aspects: first, the potential bias introduced by the fact that a considerable number of debtors are removed from the database without the reason being known, and second, the application of validation techniques to the models obtained, following the proposals of a document recently published by the BCBS.

JEL classification: C53, E37

Portada documento de trabajo 4

Published

2006-05-01

How to Cite

Balzarotti, V., Gutiérrez Girault, M., & Vallés, V. (2006). Credit scoring models with truncated samples and their validation: Working papers | 2006 | N 4. Working papers. retrieved from https://investigacionesconomicas.bcra.gob.ar/documentos_de_trabajo/article/view/420

Issue

Section

Articles