Business failure prediction using decision trees

Adrian Gepp, Kuldeep Kumar, Sukanto Bhattacharya

Research output: Contribution to journalArticleResearchpeer-review

57 Citations (Scopus)
2 Downloads (Pure)

Abstract

Accurate business failure prediction models would be extremely valuable to many industry sectors, particularly financial investment and lending. The potential value of such models is emphasised by the extremely costly failure of high-profile companies in the recent past. Consequently, a significant interest has been generated in business failure prediction within academia as well as in the finance industry. Statistical business failure prediction models attempt to predict the failure or success of a business. Discriminant and logit analyses have traditionally been the most popular approaches, but there are also a range of promising non-parametric techniques that can alternatively be applied. In this paper, the relatively new technique of decision trees is applied to business failure prediction. The numerical results suggest that decision trees could be superior predictors of business failure as compared to discriminant analysis.

Original languageEnglish
Pages (from-to)536-555
Number of pages20
JournalJournal of Forecasting
Volume29
Issue number6
Early online date25 Nov 2009
DOIs
Publication statusPublished - Sep 2010

Fingerprint

Decision trees
Decision tree
Prediction
Industry
Prediction Model
Logit
Business
Failure prediction
Business failures
Discriminant Analysis
Finance
Discriminant
Predictors
Discriminant analysis
Sector
Predict
Numerical Results
Range of data
Prediction model

Cite this

Gepp, Adrian ; Kumar, Kuldeep ; Bhattacharya, Sukanto. / Business failure prediction using decision trees. In: Journal of Forecasting. 2010 ; Vol. 29, No. 6. pp. 536-555.
@article{8448fe27dcf944d6957a10f2800ffb32,
title = "Business failure prediction using decision trees",
abstract = "Accurate business failure prediction models would be extremely valuable to many industry sectors, particularly financial investment and lending. The potential value of such models is emphasised by the extremely costly failure of high-profile companies in the recent past. Consequently, a significant interest has been generated in business failure prediction within academia as well as in the finance industry. Statistical business failure prediction models attempt to predict the failure or success of a business. Discriminant and logit analyses have traditionally been the most popular approaches, but there are also a range of promising non-parametric techniques that can alternatively be applied. In this paper, the relatively new technique of decision trees is applied to business failure prediction. The numerical results suggest that decision trees could be superior predictors of business failure as compared to discriminant analysis.",
author = "Adrian Gepp and Kuldeep Kumar and Sukanto Bhattacharya",
year = "2010",
month = "9",
doi = "10.1002/for.1153",
language = "English",
volume = "29",
pages = "536--555",
journal = "Journal of Forecasting",
issn = "0277-6693",
publisher = "John Wiley & Sons",
number = "6",

}

Business failure prediction using decision trees. / Gepp, Adrian; Kumar, Kuldeep; Bhattacharya, Sukanto.

In: Journal of Forecasting, Vol. 29, No. 6, 09.2010, p. 536-555.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Business failure prediction using decision trees

AU - Gepp, Adrian

AU - Kumar, Kuldeep

AU - Bhattacharya, Sukanto

PY - 2010/9

Y1 - 2010/9

N2 - Accurate business failure prediction models would be extremely valuable to many industry sectors, particularly financial investment and lending. The potential value of such models is emphasised by the extremely costly failure of high-profile companies in the recent past. Consequently, a significant interest has been generated in business failure prediction within academia as well as in the finance industry. Statistical business failure prediction models attempt to predict the failure or success of a business. Discriminant and logit analyses have traditionally been the most popular approaches, but there are also a range of promising non-parametric techniques that can alternatively be applied. In this paper, the relatively new technique of decision trees is applied to business failure prediction. The numerical results suggest that decision trees could be superior predictors of business failure as compared to discriminant analysis.

AB - Accurate business failure prediction models would be extremely valuable to many industry sectors, particularly financial investment and lending. The potential value of such models is emphasised by the extremely costly failure of high-profile companies in the recent past. Consequently, a significant interest has been generated in business failure prediction within academia as well as in the finance industry. Statistical business failure prediction models attempt to predict the failure or success of a business. Discriminant and logit analyses have traditionally been the most popular approaches, but there are also a range of promising non-parametric techniques that can alternatively be applied. In this paper, the relatively new technique of decision trees is applied to business failure prediction. The numerical results suggest that decision trees could be superior predictors of business failure as compared to discriminant analysis.

UR - http://www.scopus.com/inward/record.url?scp=77956385089&partnerID=8YFLogxK

U2 - 10.1002/for.1153

DO - 10.1002/for.1153

M3 - Article

VL - 29

SP - 536

EP - 555

JO - Journal of Forecasting

JF - Journal of Forecasting

SN - 0277-6693

IS - 6

ER -