Multi-class Models for Assessing the Financial Condition of Manufacturing Enterprises

Contemporary Economics (2020), Vol. 14 No. 2, pp. 219-235

17 Pages Posted: 21 Feb 2021

Date Written: June 23, 2020


Since 2007, the operating conditions of companies have changed significantly and can be described as more unpredictable. Insolvency of one company may, by the domino effect, have negative impacts on other operators. In extreme cases, these impacts can lead to their bankruptcy. Therefore, it is important to constantly monitor both the financial condition of a company and the financial condition of its business partners. In order to evaluate the financial standing of a company different types of methods can be employed. The aim of the paper was to build two models that specify more than two states of financial standing of manufacturing businesses. The use of the models enables recognition of the deteriorating financial condition of manufacturing companies a few years before insolvency is declared. The traditional discriminant model and Bayesian model were constructed. Cluster analysis was used to select classes of financial standing of the analyzed companies. The models were tested on two sets of samples. A small sample consisted of 224 (112 + 112) companies and a large sample consisted of more than 10,600 companies. The results showed that the traditional discriminant model performs better than the Bayesian model for classifying companies.

Keywords: financial standing, integrated models, manufacturing sector, cluster analysis

JEL Classification: G01, G33, L60

Suggested Citation

Tomczak, Sebastian Klaudiusz, Multi-class Models for Assessing the Financial Condition of Manufacturing Enterprises (June 23, 2020). Contemporary Economics (2020), Vol. 14 No. 2, pp. 219-235, Available at SSRN:

Sebastian Klaudiusz Tomczak (Contact Author)

Wrocław University of Science and Technology ( email )

wybrzeże Stanisława Wyspiańskiego 27
Wrocław, 50-370

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics