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.

Application of support vector machines on the basis of the first Hungarian bankruptcy model

In our study we rely on a data mining procedure known as support vector machine (SVM) on the database of the first Hungarian bankruptcy model. The models constructed are then contrasted with the results of earlier bankruptcy models with the use of classification accuracy and the area under the ROC curve. In using the SVM technique, in addition to conventional kernel functions, we also examine the possibilities of applying the ANOVA kernel function and take a detailed look at data preparation tasks recommended in using the SVM method (handling of outliers). The results of the models assembled suggest that a significant improvement of classification accuracy can be achieved on the database of the first Hungarian bankruptcy model when using the SVM method as opposed to neural networks.

Content and drivers of performance management in agency-type organizations of the hungarian public administration

The improving performance of public administration and the reform of public financing system have been on agenda in Hungary for many years, in accordance with the international trends. However, governments have not expected and supported creating of a performance-oriented public administration in a comprehensive and explicit way. Nevertheless, there are bottom-up initiatives at organizational level, which target performance-oriented organizational function. The research focuses on organizations of central public administration where the successful application of performance management methods is most likely based on the international literature. These are the so called agency-type organizations, which are in Hungary called autonomous state-administration organizations independent of the Government (e.g. Hungarian Competition Authority), government bureaus (e.g. Hungarian Central Statistical Office), and central offices subordinated to the government (either the cabinet or a ministry) (e.g. Hungarian Meteorological Service). The studied agencies are legally independent organizations with managerial autonomy based on public law. The purpose of this study is to get an overview on organizational level performance management tools applied by Hungarian agencies, and to reveal the reasons and drivers of the application of these tools. The empirical research is based on a mixed methods approach which combines both quantitative methods and qualitative procedures. The first – quantitative – phase of the author’s research was content analysis of homepages of the studied organizations. As a results she got information about all agencies and their practice related to some performance management tools. The second – qualitative – phase was based on semi-structured face-to-face interviews with some senior managers of agencies. The author selected the interviewees based on the results of the first phase, the relatively strong performance orientation was an important selection criteria.