Cluster analysis of regions of the Russian Federation by employee needs based on machine learning methods

Abstract

Importance: this paper reveals the problems of clustering regions of the Russian Federation as a necessary tool for developing the country’s human resources potential. In turn, the development of the country’s human resources potential in various sectors of the economy should occur systematically, taking into account the trend in demand for personnel with the necessary set of competencies and the existing human resources potential. Purpose: clustering of regions according to the needs of organizations for workers to fill vacant jobs by professional groups and subjects of the Russian Federation. Research design: the authors of the study implemented a K-means clustering algorithm using the scikit-learn library in Python, which is aimed at selecting centroids in order to minimize the sum of squared distances within a cluster. The number of clusters for the data set was determined using the elbow method. The study identified four clusters of regions of the Russian Federation. The first cluster mostly includes regions of the Southern and Northwestern Federal Districts, as well as the cities of Moscow and St. Petersburg. The second cluster, the most numerous in composition, includes many regions of the Volga and Central Federal Districts. The third cluster mainly includes regions of the North Caucasian Federal District. The fourth cluster includes regions of the Central, Siberian, and Far Eastern Federal Districts. Results: the developed methodology for conducting cluster analysis can contribute to the development of human resources potential of the Russian Federation. In particular, it can become a tool in solving the issue of optimizing personnel training, increasing labor mobility, effectively distributing resources, and creating conditions for sustainable economic growth.