Neural Networks in Bankruptcy Prediction - A Comparative Study on the Basis of the First Hungarian Bankruptcy Model

The article attempts to answer the question whether or not the latest bankruptcy prediction techniques are more reliable than traditional mathematical–statistical ones in Hungary. Simulation experiments carried out on the database of the first Hungarian bankruptcy prediction model clearly prove that bankruptcy models built using artificial neural networks have higher classification accuracy than models created in the 1990s based on discriminant analysis and logistic regression analysis. The article presents the main results, analyses the reasons for the differences and presents constructive proposals concerning the further development of Hungarian bankruptcy prediction.

Neural networks would 'vote' according to Borda's Rule

Can neural networks learn to select an alternative based on a systematic aggregation of convicting individual preferences (i.e. a 'voting rule')? And if so, which voting rule best describes their behavior? We show that a prominent neural network can be trained to respect two fundamental principles of voting theory, the unanimity principle and the Pareto property. Building on this positive result, we train the neural network on profiles of ballots possessing a Condorcet winner, a unique Borda winner, and a unique plurality winner, respectively. We investigate which social outcome the trained neural network chooses, and find that among a number of popular voting rules its behavior mimics most closely the Borda rule. Indeed, the neural network chooses the Borda winner most often, no matter on which voting rule it was trained. Neural networks thus seem to give a surprisingly clear-cut answer to one of the most fundamental and controversial problems in voting theory: the determination of the most salient election method.

Long-term dynamic patterns and diversity of phytoplankton communities in a large eutrophic river (the case of River Danube, Hungary)

In this paper we present the composition, seasonal dynamics and fluctuations in diversity of the phytoplankton in the Danube River over 24 years. Weekly samplings were conducted at one section of the river at Göd, in the 1669 river kilometer segment. The change in the phytoplankton community structure was analyzed in relation of water temperature and discharge means. Our findings support the opinion that the Danube is very rich in species, although many of the species are rare and could be described only as coloring species. Results indicate trends in the phytoplankton abundance, which are only detectable in long-term studies. By the help of diversity indices we have observed an increase in the phytoplankton community diversity. With the relevant information, an explanation of the significant changes in diversity and richness was formed. Our goals were a construction of a solid database of the phytoplankton, examining the seasonal dynamics of the phytoplankton through a 24 year long study and to see the most important changing factors of the community. The results of this study are to assist and help future model developments to predict the phytoplankton seasonal dynamic patterns.

Patterns and Drivers of the Agri-Food Intra-Industry Trade of European Union Countries

This paper investigates the drivers of agri-food intra-industry trade (IIT) indices in the European Union (EU-27) member states during the period from 2000–2011. The increased proportion of IIT in matched two-way agri-food trade of the EU-27 member states is consistent with economic integration and economic growth. When export prices were at least 15% higher than the import prices, high-vertical IIT, increased for most member states. This finding suggests that quality improvements occurred when comparing agri-food exports to similar imports of agri-food products. The IIT indices for both horizontal and vertical IIT are positively associated with higher economic development levels, new EU membership and EU enlargement. Additionally, as higher levels of economic development decreases, the size of the economy and marginal IIT increases the effects of agri-food trade liberalization on the costs of the labor market adjustment. Understanding how improvements in agri-food trade quality impact agribusiness and managerial competitiveness reveal significant policy implications.