Assessing the Level of Employment in the Informal Sector of the Economy of Russian Regions Using Modern Machine Learning Methods

• Published in: Review of Business and Economics Studies Vol. 12; no. 4; pp. 42 - 57
• Main Authors: Aleksey Nikolaevich Borisov, Aleksandr Ivanovich Borodin, Roman Vladimirovich Gubarev, Evgeny Ivanovich Dzuyba, Oksana Mikhaylovna Kulikova
• Format: Journal Article
• Language: English
• Published: Financial University 01.12.2024
• Subjects: classification; clustering; employment level; forecasting; informal sector of the economy; machine learning; precariat; regions of russia
• ISSN: 2308-944X; 2311-0279
• DOI: 10.26794/2308-944X-2024-12-4-42-57

The global trend is mass employment of the population in the informal sector of the economy. At the same time, only in economically developed countries of the world such workers have relatively good working conditions. At the current stage of development, Russia is among the group of actively economically developing countries of the world. Therefore, the improvement of the mechanism of state social protection of those employed in the informal sector of the economy remains an urgent relevant issue for our country, which, in turn, implies monitoring of the situation. The purpose of this study is to develop tools for such monitoring with the help of artificial intelligence (more precisely, modern machine learning methods). According to the results of cluster analysis carried out using the k-means method in the Python programming language, it was found that in modern Russia there is a high degree of differentiation of regions by the level of employment in the informal sector of the economy. At the same time, most of the subjects of the Russian Federation are characterised by the same situation as in economically developing countries of Eastern Europe (Bosnia and Herzegovina, Serbia, Czech Republic). Four regions of Russia (from the North Caucasus Federal District) have an abnormally high level of employment in the informal sector of the economy comparable only with economically developing countries of Asia, Africa, North and South America. In the course of solving the classification problem using a modern machine learning method (LightGBM), the key factors affecting the level of employment in the informal sector of the economy of Russian regions were identified. According to the classification results, we can conclude that a cardinal change in the current situation is not expected in the future. Therefore, for modern Russia, it is necessary to improve the state social policy for a significant part of the regions. The results of the empirical study can be applied to improve the effectiveness of the state social policy of the Russian Federation. Thus, in particular, it will be possible to specify the amount of financial resources required for additional social support of the employed population of certain regions of our country.