No abstract

Abstract. The paper highlights theoretical construct of crisis situation in a company emphasizing the methodological positions of a social phenomenon. Applying systemic analysis of crisis situation in a company the paper discusses hardly spread social phenomenon, i.e. occurrence and expression of crisis situation in a company. On the basis of retrospective analysis of crisis situation, both crisis environment and bankruptcy features are presented and principal keywords defi ned with reference to crisis in a company as a social phenomenon and related to its environment: human, company-based, national and global. It shows the complexity of the scientifi c research object, that brings meaningful input into the analysis of crisis features in company life cycle. The paper aims at discussing and presenting critical reviews of crisis situation interpretations with emphasis on methodological positions of social phenomenon in different disciplines. The differences and links between crisis and crisis situation are also explained. Through explanation of logical construct of the paper, the authors specify crisis concept in a company: distinguishing negative changes in a company, that make the company staff apply crisis communication process and instrumentalities. In the above mentioned context the problem of crisis situation in a company remains signifi cant from psychological, social and economic and managerial perspectives.

The aim of this research was to model bankruptcy dependency of Lithuanian enterprises on their financial ratios and its dynamics over time by the integration of artificial neural networks and fuzzy logic technology using Adaptive Network – based Fuzzy Inference System (ANFIS). We used data from financial reports for three years’ of 230 Lithuanian going and failed enterprises. Input variables used for the ANFIS model training and testing composed of 13 financial ratios of the last year before bankruptcy and 13 variables characterizing changes of that ratios over time. It was checked 1716 subsets of input variables, each subset containing five input variables. This way the ANFIS model and the best subset of predictive variables with minimal training errors was found. Test of that model showed that percentage of right failure and success predictions reached 80 %. Fuzzy rules of the ANFIS were used to construct interpretable rules base, which can be useful for enterprise managers as knowledge for the linguistic diagnosis of failure or financial problems.