Credit scoring attracts special attention of financial institutions. In recent years, deep learning methods have been particularly interesting. In this paper, we compare the performance of ensemble deep learning methods based on decision trees with the best traditional method, logistic regression, and the machine learning method benchmark, support vector machines. Each method tests several different algorithms. We use different performance indicators. The research focuses on standard datasets relevant for this type of classification, the Australian and German datasets. The best method, according to the MCC indicator, proves to be the ensemble method with boosted decision trees. Also, on average, ensemble methods prove to be more successful than SVM.
The degree of the banking sector concentration is a structural variable and refers to the number of banks in the system and the degree of their market power. The importance of measuring concentration in the banking sector stems from the causal relationship between the market structure and the competitive behaviour of market participants. Traditional models measuring the banking sector competition proceed from the market structure and concentration measures. In contrast, modern approaches to measuring competition rely on non-structural models and analysis of the behaviour of market participants. The paper analyzes the degree of concentration and competition in the banking sector of the Republic of Serbia. The traditional and most frequently used indices, the concentration ratio and the Herfindahl-Hirschman index, are used to measure concentration. The values of these indices show low banking sector concentration but a rise in the observed period. The values of the comprehensive industrial concentration index and the entropy coefficient confirm the concentration absence in the banking sector of the Republic of Serbia. In addition to the usual banking sector concentration measures, the authors use the Linda index to assess the banking sector concentration and competitiveness, to show the absence of an oligopolistic structure in terms of total balance sheet assets, lending and deposit activity of banks.
Visual representation is one of the key structural elements of a textbook. A historical map is a graphic representation of the geographical area where historical events took place at a certain time. The subject of this research is the analysis of the use of a historical map in the Science and Social Studies textbooks for the fourth grade of primary school. In this paper, we have analyzed whether these textbooks contain historical maps, their number, whether they are titled, whether there are additional explanations or legends, and to what extent a historical map is referred to by the accounts in the text of the textbooks, on the basis of which students should, by independently interpreting, analyzing and reading the map, come to certain conclusions and knowledge. The method used is the content analysis method. The analysis indicates that all five textbooks contain historical maps, although they are not explicitly mentioned as a term in teaching and learning programs. Historical maps should enable students to acquire more permanent knowledge through independent work and map reading as well as develop new concepts with regard to historical content. Studying the use of historical maps in the Science and Social Studies textbooks is important for improving the teaching process.
Audit and credit rating agencies have a significant responsibility in assessing company creditworthiness and giving opinions on the client’s ability to continue business in the future, most often the next fiscal year. Responsibility is even greater when it comes to banks and their creditworthiness. The financial crisis of 2007 and the bankruptcy of a number of banks and other financial institutions imposed a need to seek accountability for the “delayed” reaction of regulatory bodies and significant fiscal consequences of the crisis. The aim of the paper is to evaluate the efficiency of credit rating agencies and external audit in assessing the creditworthiness of companies and banks, not for the purpose of finding their individual responsibilities, but to look at possible coordinated and joint actions to prevent future crisis events.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.