An implementation of Soft Set Theory in the Variables Selection Process for Corporate Failure Prediction Models. Evidence from NASDAQ Listed Firms

Apostolos G. Christopoulos, Ioannis G. Dokas, Iraklis Kollias and John Leventides

Bulletin of Applied Economics, 2019, vol. 6, issue 1, 1-20

Abstract: The foremost aim of this paper is to propose a reliable methodology regarding the selection process of financial ratios as input variables in the construction of corporate failure prediction models. In this paper soft set theory is introduced. In the first stage, emphasis is given on the state of liquidity as a measure for the classification of a group of NASDAQ listed firms in two a priori groups (failed and non-failed) using four liquidity criteria as follows: current ratio 1, current liabilities to total liabilities 70%, Equity to Liabilities 0 and Total Debt to Total Assets 70%. In the second stage, a parameter reduction algorithm is applied in order to determine, from a group of ratios, those which provide significant predictive power and optimize the classification accuracy of the model. A tabular representation of a soft set is constructed in order to select the input variables in the model based on the importance degree of each financial ratio. The findings show that the primary assumptions relevant to the definition of failure based on the soft set theory approach are confirmed, though the majority of the significant ratios in the applied sample of listed firms are related to the analysis of profitability.

Keywords: Failure prediction; definition of failure; liquidity and profitability; financial ratios; soft set theory; Logistic regression. (search for similar items in EconPapers)
JEL-codes: C2 C4 G33 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.riskmarket.co.uk/bae/journals-articles ... nload=attachment.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rmk:rmkbae:v:6:y:2019:i:1:p:1-20

Access Statistics for this article

Bulletin of Applied Economics is currently edited by Eleftherios Spyromitros

More articles in Bulletin of Applied Economics from Risk Market Journals
Bibliographic data for series maintained by Eleftherios Spyromitros-Xioufis ().