The effectiveness of discriminant models based on the example of the manufacturing sector

Abstract

The objective of this paper is to select the best models of bankruptcy prediction that can indicate the deteriorating situation of a company several years before bankruptcy occurs. There are a lot of methods for evaluating the financial statements of enterprises, but only a few can assess a company as a whole and recognise sufficiently early the deteriorating financial standing of a business. The matrix method was used to classify companies in order to assess the models. The correctness of the classification made by the models was tested based on data covering a period of five years before the bankruptcy of enterprises. To analyse the effectiveness of these discriminant models, the financial reports of manufacturing companies were used. Analysis of 33 models of bankruptcy prediction shows that only 5 models were characterized by sufficient predictive ability in the five years before the bankruptcy of enterprises. The results obtained show that so far a unique, accurate, optimal model, by which companies could be assessed with very high efficiency, has not been identified. That is why it is vital to continue research related to the construction of models enabling accurate evaluation of the financial condition of businesses. Matrix method was used for classifying companies in order to verify the models. The correctness of classification of models was tested in the period of five years before the bankruptcy of enterprises. To analyze the effectiveness of the discriminant models the financial reports of manufacturing companies were used. The analysis of 33 bankruptcy prediction models shows that only 5 models were characterized by sufficient predictive ability in the five years before the bankruptcy of enterprises. Obtained results have shown that so far a unique, perfect, the best model, by which companies could be estimated with very high efficiency, has not been established. That is why, it is vital to continue research related to the building of models enabling evaluation of the financial condition of businesses.