Choosing a method for predicting economic performance of companies

Abstract

This paper reports on the eff orts to fi nd a method for predicting economic results of companies. The input data fi les consist of 93 profi table companies and 93 bankrupt fi rms. From the total number of 93 fi rms in both categories, data of 72 fi rms served for establishing a classifi cation criterion, and for the rest of 21 fi rms, a prognosis of their economic development was performed. The classifi cation criterion for prognosticating the future economic development has been established by applications of discriminate analysis, logit analysis, and artifi cial neural network methods. The application of artifi cial neural networks has provided for better classifi cation accuracies of 90,48 % for successful fi rms, and 100 % for bankrupt fi rms.