Clustering Russian regions as a method of predictive analytics for effective regulation of informal employment

Abstract

Informal employment covers significant segments of the Russian population. This prevents the increase of poverty, inequality and the growth of well-being, creating «traps» of sustainable development. The article is devoted to the study of the main causes of the spread of informal employment in the labor market of Russian regions using expert analytical methods, analysis of statistical data series and clustering. Classification of regions was built on the basis of the k-means algorithm, which made it possible to minimize variance within regional groups and build clusters based on weighted standardized data. In each cluster, regions have similar characteristics in terms of criteria for the ratio of shadow employment and income. This study is one of the first attempts to cluster regions using Ward's hierarchical method according to the criteria «income of the population - informal employment». Clusters of Russian regions constructed and visualized using the RStudio programming language showed that informal employment strongly correlates with the «low welfare» zone: the lower incomes of the population, the greater part of it works informally. The scientific novelty of the study is to identify the main factor of high informal employment in Russian regions - relative and absolute poverty of the population. The practical significance of reducing shadow employment lies not only in improving the efficiency of regulation of regional labor markets, increasing the revenues of the budget system and the standard of living of the population, but also in modernizing approaches to ensuring the demographic security of the regions of Russia.