A new mixture model for the estimation of credit card exposure at default

Mindy Leow, Jonathan Crook

Research output: Contribution to journalArticlepeer-review

Abstract

Using a large portfolio of historical observations on defaulted loans, we estimate Exposure at Default at thelevel of the obligor by estimating the outstanding balance of an account, not only at the time of default, butat any time over the entire loan period. We theorize that the outstanding balance on a credit card account atany time during the loan is a function of the spending by the borrower and is also subject to the credit limitimposed by the card issuer. The predicted value is modelled as a weighted average of the estimated balanceand limit, with weights depending on how likely the borrower is to have a balance greater than the limit. Theweights are estimated using a discrete-time repeated events survival model to predict the probability of anaccount having a balance greater than its limit. The expected balance and expected limit are estimated usingtwo panel models with random effects. We are able to get predictions which, overall, are more accurate foroutstanding balance, not only at the time of default, but at any time over the entire default loan period, thanany other particular technique in the literature
Original languageEnglish
Pages (from-to)487-497
JournalEuropean Journal of Operational Research
Volume249
Issue number2
Early online date9 Oct 2015
DOIs
Publication statusPublished - Mar 2016

Keywords

  • risk management
  • forecasting
  • panel models
  • survival models
  • macroeconmic variables
  • time-varying covariates

Fingerprint Dive into the research topics of 'A new mixture model for the estimation of credit card exposure at default'. Together they form a unique fingerprint.

Cite this