Variable reduction, sample selection bias and bank retail credit scoring

A.P. Marshall, L. Tang, Alistair Milne

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

This paper investigates the effect of including the customer loan approval process to the estimation of loan performance and explores the influence of sample selection bias in predicting the probability of default. The bootstrap variable reduction technique is applied to reduce the variable dimension for a large dataset drawn from a major UK retail bank. The results show a statistically significant correlation between the loan approval and performance processes. We further demonstrate an economically significant improvement in forecasting performance when taking into account sample selection bias. We conclude that financial institutions can obtain benefits by correcting for sample selection bias in their credit scoring models.
LanguageEnglish
Pages501–512
Number of pages12
JournalJournal of Empirical Finance
Volume17
Issue number3
DOIs
Publication statusPublished - Jun 2010

Fingerprint

Loans
Sample selection bias
Credit scoring
Retail
Financial institutions
Process performance
Bootstrap
Probability of default
Forecasting performance

Keywords

  • bootstrap variable selection
  • credit scoring
  • loan performance forecasting
  • sample selection bias

Cite this

@article{e03522e631df4fd782399a704a002e6e,
title = "Variable reduction, sample selection bias and bank retail credit scoring",
abstract = "This paper investigates the effect of including the customer loan approval process to the estimation of loan performance and explores the influence of sample selection bias in predicting the probability of default. The bootstrap variable reduction technique is applied to reduce the variable dimension for a large dataset drawn from a major UK retail bank. The results show a statistically significant correlation between the loan approval and performance processes. We further demonstrate an economically significant improvement in forecasting performance when taking into account sample selection bias. We conclude that financial institutions can obtain benefits by correcting for sample selection bias in their credit scoring models.",
keywords = "bootstrap variable selection, credit scoring, loan performance forecasting, sample selection bias",
author = "A.P. Marshall and L. Tang and Alistair Milne",
year = "2010",
month = "6",
doi = "10.1016/j.jempfin.2009.12.003",
language = "English",
volume = "17",
pages = "501–512",
journal = "Journal of Empirical Finance",
issn = "0927-5398",
number = "3",

}

Variable reduction, sample selection bias and bank retail credit scoring. / Marshall, A.P.; Tang, L.; Milne, Alistair.

In: Journal of Empirical Finance, Vol. 17, No. 3, 06.2010, p. 501–512.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Variable reduction, sample selection bias and bank retail credit scoring

AU - Marshall, A.P.

AU - Tang, L.

AU - Milne, Alistair

PY - 2010/6

Y1 - 2010/6

N2 - This paper investigates the effect of including the customer loan approval process to the estimation of loan performance and explores the influence of sample selection bias in predicting the probability of default. The bootstrap variable reduction technique is applied to reduce the variable dimension for a large dataset drawn from a major UK retail bank. The results show a statistically significant correlation between the loan approval and performance processes. We further demonstrate an economically significant improvement in forecasting performance when taking into account sample selection bias. We conclude that financial institutions can obtain benefits by correcting for sample selection bias in their credit scoring models.

AB - This paper investigates the effect of including the customer loan approval process to the estimation of loan performance and explores the influence of sample selection bias in predicting the probability of default. The bootstrap variable reduction technique is applied to reduce the variable dimension for a large dataset drawn from a major UK retail bank. The results show a statistically significant correlation between the loan approval and performance processes. We further demonstrate an economically significant improvement in forecasting performance when taking into account sample selection bias. We conclude that financial institutions can obtain benefits by correcting for sample selection bias in their credit scoring models.

KW - bootstrap variable selection

KW - credit scoring

KW - loan performance forecasting

KW - sample selection bias

U2 - 10.1016/j.jempfin.2009.12.003

DO - 10.1016/j.jempfin.2009.12.003

M3 - Article

VL - 17

SP - 501

EP - 512

JO - Journal of Empirical Finance

T2 - Journal of Empirical Finance

JF - Journal of Empirical Finance

SN - 0927-5398

IS - 3

ER -