The application of Kohonen networks for identification of leaders in the trade sector in Czechia
Research background: The trade sector is considered to be the power of economy, in developing countries in particular. With regard to the Czech Republic, this field of the national economy constitutes the second most significant employer and, at the same time, the second most significant contributor to GNP. Apart from traditional methods of business analyzing and identifying leaders, artificial neural networks are widely used. These networks have become more popular in the field of economy, although their potential has yet to be fully exploited.
Purpose of the article: The aim of this article is to analyze the trade sector in the Czech Republic using Kohonen networks and to identify the leaders in this field.
Methods: The data set consists of complete financial statements of 11,604 enterprises that engaged in trade activities in the Czech Republic in 2016. The data set is subjected to cluster analysis using Kohonen networks. Individual clusters are subjected to the analysis of absolute indicators and return on equity which, apart from other, shows a special attraction of individual clusters to potential investors. Average and absolute quantities of individual clusters are also analyzed, which means that the most successful clusters of enterprises in the trade sector are indicated.
Findings & Value added: The results show that a relatively small group of enter-prises enormously influences the development of the trade sector, including the whole economy. The results of analyzing 319 enterprises showed that it is possible to predict the future development of the trade sector. Nevertheless, it is also evident that the trade sector did not go well in 2016, which means that investments of owners are minimal.
Abecassis-Moedas, C., & Mahmoud-Jouini, S. B. (2008). Absorptive capacity and source-recipient knowledge complementarity in designing new products: an empirically derived framework. Journal of Product Innovation Management, 25(5). doi: 10.1111/j.1540-5885.2008.00315.x.
Balcerzak, A. P., Klieštik, T., Streimikiene, D., & Smrčka, L. (2017). Non-parametric approach to measuring the efficiency of banking sectors in European Union countries. Acta Polytechnica Hungarica, 14(7). doi: 10.12700/ APH.14.7.2017.7.4.
Dyhdalewicz, A. (2017). Innovation of trading companies in relation to the content of annual reports: research results In M. Cingula, M. Przygoda & K. Detelj (Eds.). 23rd international scientific conference on economic and social development : ESD'2017 : book of proceedings.
Doganay, M., & Kocsoy, M. (2011). A field study concerning the effects of economic crisis on international trading companies and the measures taken. African Journal of Business Management, 55(22). doi: 10.5897/AJBM11.315.
Gavurová, B., Packová, M., Mišanková, M., & Smrčka, L. (2017). Predictive potential and risks of selected bankruptcy prediction models in the Slovak business environment. Journal of Business Economics and Management, 18(6). doi: 10.3846/16111699.2017.1400461.
Hossain, S., Ong, Z. C., Ismail, Z., Noroozi, S., & Khoo, S. Y. (2017). Artificial neural networks for vibration based inverse parametric identifications: a review. Applied Soft Computing, 52. doi: 10.1016/j.asoc.2016.12.014.
Klieštik, T., Mišankova, M., Valášková, K., & Švábová, L. (2018). Bankruptcy prevention: new effort to reflect on legal and social changes. Science and Engineering Ethics, 24(2). doi: 10.1007/s11948-017-9912-4.
Koh, H. L.S, The, Y., & Tan, W. K. (2016). Global financial crisis: origin and management. International Journal of Economics and Financial Issues, 6(3).
Konečný, V., Trenz, O., & Svobodová, E. (2010). Classification of companies with the assistance of self-learning neural networks. Agricultural Economics, 56(2), 51-58. doi: 10.17221/60/2009-AGRICECON.
Kramoliš, J., Staňková, P., & Richtr, M. (2015). The importance of design in business practices of czech companies. E M Ekonomie a Management, 18(2). doi. 10.15240/tul/001/2015-2-011.
Krulický, T. (2019). Using Kohonen networks in the analysis of transport companies in the Czech Republic. SHS Web of Conferences: Innovative Economic Symposium 2018 – Milestones and Trends of World Economy, 61. doi: 10.1051/shsconf/20196101010.
Lumpkin, G. G., & Dess, G. T. (2005). The role of entrepreneurial orientation in stimulating effective corporate entrepreneurship. Academy of Management Executive, 19(1). doi: 10.5465/AME.2005.15841975.
Machová, V., & Vochozka, M. (2019). Analysis of business companies based on artificial neural networks. SHS Web of Conferences: Innovative Economic Symposium 2018 – Milestones and Trends of World Economy, 61. doi: 10.1051/shsconf/20196101013.
Petrů, N., Havlíček, K., & Tomášková, A. (2018). Comparison of marketing vitality of family and non family companies doing business in the Czech Republic. Economics and Sociology, 11(2). doi: 10.14254/2071-789X.2018/11-2/10.
Santin, D. (2008). On the approximation of production functions: a comparison of artificial neural networks frontiers and efficiency techniques. Applied Economics Letters, 15(8). doi: 10.1080/13504850600721973.
Smith, K. A., & Gupta, J. N. D. (2000). Neural networks in business: techniques
and applications for the operations researcher. Computers & Operations Research, 27(11-12). doi: 10.1016/S0305-0548(99)00141-0.
Šuleř, P. (2017). Using Kohonen neural networks to identify the bankruptcy of enterprises: case study based on construction companies in South Bohemian region. In Proceedings of the 5th international conference innovation management, entrepreneurship and sustainability.
Vochozka, M. (2017). Analysis of companies operating in manufacturing industry
in the Czech Republic using Kohonen networks. In 17th international scientific conference globalization and its socio-economic consequences.
Vochozka, M., Klieštik, T., Klieštiková, J., & Sion, G. (2018). Participating in a highly automated society: How artificial intelligence disrupts the job market. Economics, Management, and Financial Markets, 13(4). doi: 10.22381/EMF M13420185.
This work is licensed under a Creative Commons Attribution 4.0 International License.