Systematic review of bankruptcy prediction models: towards a framework for tool selection

Hafiz A Alaka, Lukumon O Oyedele, Hakeem A Owolabi, Vikas Kumar, Saheed O Ajayi, Olugbenga O Akinade, Muhammad Bilal

Research output: Contribution to journalArticleResearchpeer-review

Abstract

The bankruptcy prediction research domain continues to evolve with many new different predictive models developed using various tools. Yet many of the tools are used with the wrong data conditions or for the wrong situation. Using the Web of Science, Business Source Complete and Engineering Village databases, a systematic review of 49 journal articles published between 2010 and 2015 was carried out. This review shows how eight popular and promising tools perform based on 13 key criteria within the bankruptcy prediction models research area. These tools include two statistical tools: multiple discriminant analysis and Logistic regression; and six artificial intelligence tools: artificial neural network, support vector machines, rough sets, case based reasoning, decision tree and genetic algorithm. The 13 criteria identified include accuracy, result transparency, fully deterministic output, data size capability, data dispersion, variable selection method required, variable types applicable, and more. Overall, it was found that no single tool is predominantly better than other tools in relation to the 13 identified criteria. A tabular and a diagrammatic framework are provided as guidelines for the selection of tools that best fit different situations. It is concluded that an overall better performance model can only be found by informed integration of tools to form a hybrid model. This paper contributes towards a thorough understanding of the features of the tools used to develop bankruptcy prediction models and their related shortcomings.
Original languageEnglish
Pages (from-to)164-184
Number of pages21
JournalExpert Systems with Applications
Volume94
Early online date26 Oct 2017
DOIs
Publication statusPublished - 15 Mar 2018

Fingerprint

Case based reasoning
Discriminant analysis
Decision trees
Transparency
Artificial intelligence
Support vector machines
Logistics
Genetic algorithms
Neural networks
Industry

Keywords

  • Bankruptcy prediction tools
  • financial ratios
  • error types
  • systematic review
  • tool selection framework
  • artificial intelligence tools
  • statistical tools

Cite this

Alaka, H. A., Oyedele, L. O., Owolabi, H. A., Kumar, V., Ajayi, S. O., Akinade, O. O., & Bilal, M. (2018). Systematic review of bankruptcy prediction models: towards a framework for tool selection. Expert Systems with Applications, 94, 164-184. https://doi.org/10.1016/j.eswa.2017.10.040
Alaka, Hafiz A ; Oyedele, Lukumon O ; Owolabi, Hakeem A ; Kumar, Vikas ; Ajayi, Saheed O ; Akinade, Olugbenga O ; Bilal, Muhammad. / Systematic review of bankruptcy prediction models: towards a framework for tool selection. In: Expert Systems with Applications. 2018 ; Vol. 94. pp. 164-184.
@article{27d6e7b1d3e24923b3d358966db77956,
title = "Systematic review of bankruptcy prediction models: towards a framework for tool selection",
abstract = "The bankruptcy prediction research domain continues to evolve with many new different predictive models developed using various tools. Yet many of the tools are used with the wrong data conditions or for the wrong situation. Using the Web of Science, Business Source Complete and Engineering Village databases, a systematic review of 49 journal articles published between 2010 and 2015 was carried out. This review shows how eight popular and promising tools perform based on 13 key criteria within the bankruptcy prediction models research area. These tools include two statistical tools: multiple discriminant analysis and Logistic regression; and six artificial intelligence tools: artificial neural network, support vector machines, rough sets, case based reasoning, decision tree and genetic algorithm. The 13 criteria identified include accuracy, result transparency, fully deterministic output, data size capability, data dispersion, variable selection method required, variable types applicable, and more. Overall, it was found that no single tool is predominantly better than other tools in relation to the 13 identified criteria. A tabular and a diagrammatic framework are provided as guidelines for the selection of tools that best fit different situations. It is concluded that an overall better performance model can only be found by informed integration of tools to form a hybrid model. This paper contributes towards a thorough understanding of the features of the tools used to develop bankruptcy prediction models and their related shortcomings.",
keywords = "Bankruptcy prediction tools, financial ratios, error types, systematic review, tool selection framework, artificial intelligence tools, statistical tools",
author = "Alaka, {Hafiz A} and Oyedele, {Lukumon O} and Owolabi, {Hakeem A} and Vikas Kumar and Ajayi, {Saheed O} and Akinade, {Olugbenga O} and Muhammad Bilal",
year = "2018",
month = "3",
day = "15",
doi = "10.1016/j.eswa.2017.10.040",
language = "English",
volume = "94",
pages = "164--184",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",

}

Alaka, HA, Oyedele, LO, Owolabi, HA, Kumar, V, Ajayi, SO, Akinade, OO & Bilal, M 2018, 'Systematic review of bankruptcy prediction models: towards a framework for tool selection', Expert Systems with Applications, vol. 94, pp. 164-184. https://doi.org/10.1016/j.eswa.2017.10.040

Systematic review of bankruptcy prediction models: towards a framework for tool selection. / Alaka, Hafiz A; Oyedele, Lukumon O; Owolabi, Hakeem A; Kumar, Vikas; Ajayi, Saheed O; Akinade, Olugbenga O; Bilal, Muhammad.

In: Expert Systems with Applications, Vol. 94, 15.03.2018, p. 164-184.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Systematic review of bankruptcy prediction models: towards a framework for tool selection

AU - Alaka, Hafiz A

AU - Oyedele, Lukumon O

AU - Owolabi, Hakeem A

AU - Kumar, Vikas

AU - Ajayi, Saheed O

AU - Akinade, Olugbenga O

AU - Bilal, Muhammad

PY - 2018/3/15

Y1 - 2018/3/15

N2 - The bankruptcy prediction research domain continues to evolve with many new different predictive models developed using various tools. Yet many of the tools are used with the wrong data conditions or for the wrong situation. Using the Web of Science, Business Source Complete and Engineering Village databases, a systematic review of 49 journal articles published between 2010 and 2015 was carried out. This review shows how eight popular and promising tools perform based on 13 key criteria within the bankruptcy prediction models research area. These tools include two statistical tools: multiple discriminant analysis and Logistic regression; and six artificial intelligence tools: artificial neural network, support vector machines, rough sets, case based reasoning, decision tree and genetic algorithm. The 13 criteria identified include accuracy, result transparency, fully deterministic output, data size capability, data dispersion, variable selection method required, variable types applicable, and more. Overall, it was found that no single tool is predominantly better than other tools in relation to the 13 identified criteria. A tabular and a diagrammatic framework are provided as guidelines for the selection of tools that best fit different situations. It is concluded that an overall better performance model can only be found by informed integration of tools to form a hybrid model. This paper contributes towards a thorough understanding of the features of the tools used to develop bankruptcy prediction models and their related shortcomings.

AB - The bankruptcy prediction research domain continues to evolve with many new different predictive models developed using various tools. Yet many of the tools are used with the wrong data conditions or for the wrong situation. Using the Web of Science, Business Source Complete and Engineering Village databases, a systematic review of 49 journal articles published between 2010 and 2015 was carried out. This review shows how eight popular and promising tools perform based on 13 key criteria within the bankruptcy prediction models research area. These tools include two statistical tools: multiple discriminant analysis and Logistic regression; and six artificial intelligence tools: artificial neural network, support vector machines, rough sets, case based reasoning, decision tree and genetic algorithm. The 13 criteria identified include accuracy, result transparency, fully deterministic output, data size capability, data dispersion, variable selection method required, variable types applicable, and more. Overall, it was found that no single tool is predominantly better than other tools in relation to the 13 identified criteria. A tabular and a diagrammatic framework are provided as guidelines for the selection of tools that best fit different situations. It is concluded that an overall better performance model can only be found by informed integration of tools to form a hybrid model. This paper contributes towards a thorough understanding of the features of the tools used to develop bankruptcy prediction models and their related shortcomings.

KW - Bankruptcy prediction tools

KW - financial ratios

KW - error types

KW - systematic review

KW - tool selection framework

KW - artificial intelligence tools

KW - statistical tools

UR - http://www.mendeley.com/research/systematic-review-bankruptcy-prediction-models-towards-framework-tool-selection

U2 - 10.1016/j.eswa.2017.10.040

DO - 10.1016/j.eswa.2017.10.040

M3 - Article

VL - 94

SP - 164

EP - 184

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -