Credit Scoring Models: Missing Information and the Use of Data from a Credit Register

Authors

  • Fernando Castelpoggi Central Bank of Argentina
  • Verónica Balzarotti Central Bank of Argentina

Keywords:

Credit Registers, Credit Risk, Credit Scoring, Information Sharing, Imputation, Missing Data

Abstract

The main objective of this paper is to study the problem introduced by the lack of information on some debtors' credit behavior in the databases used to develop credit scoring models and the use of behavioral information contained at a Credit Register as a potential solution. Two problems are addressed (i) the need to provide an estimate of debtors' credit risk whose behavior is unknown (because they are removed from the databases without the reason being recorded), and (ii) the estimation of the impact of not taking into account the lack of this data in the risk assessment of the entities' portfolios. The fundamental strategy will be to use the credit behavior of debtors in other entities, registered at the Credit Register.

JEL classification: G21 ; G28 ; D81 ; C35

Downloads

Download data is not yet available.

Downloads

Published

2009-12-01

How to Cite

Castelpoggi, F. and Balzarotti, V. (2009) “Credit Scoring Models: Missing Information and the Use of Data from a Credit Register ”, Ensayos Económicos, (56), pp. 95–156. available at: https://investigacionesconomicas.bcra.gob.ar/ensayos_economicos_bcra/article/view/324 (accessed: 1 May 2025).

Issue

No. 56 (2009): Ensayos Económicos

Section

Articles