Cluster analysis of Russian Federation subjects by socioeconomic indicators characterizing potential for development of the secondary vocational education system

• Published in: Nauka Krasnoi͡a︡rʹi͡a Vol. 14; no. 2; pp. 143 - 165
• Main Authors: Samtsevich, Pavel I., Yankov, Sergey G., Kornilova, Elena V.
• Format: Journal Article
• Language: English
• Published: Science and Innovation Center Publishing House 30.06.2025
• Subjects: cluster analysis; k-means method; principal component analysis; secondary vocational education; socio-economic development; strategic development; subjects of the russian federation
• ISSN: 2070-7568; 2782-3261
• DOI: 10.12731/2070-7568-2025-14-2-300

In the modern world, data is an important basis for making management decisions, coordinating actions, controlling and analyzing processes occurring in society. However, the volumes of data characterizing various aspects of contemporary social life are as large as they are complex to process. The subject of research is such an important part of social life as education, specifically training in educational institutions implementing programs of secondary vocational education (hereinafter referred to as SPVO). The rationale for the study stems from the idea that the development of the SPVO system can solve a number of socio-economic problems in regions. The main hypothesis of the study is that knowledge of the socio-economic characteristics of regions allows forming an optimal state policy in the field of SPVO. The objectives of the study were to identify factors influencing the demand for SPVO, conduct cluster analysis of regions using the k-means method, determine and describe cluster profiles, assess the contribution of each factor to shaping the demand for SPVO and its impact on the development of the SPVO system. The methodology of the study involved reducing the dimensionality of the data using principal component analysis. Clusterization was carried out by the k-means method. Euclidean norm was used as a measure of distance between objects within clusters. Clusterization was performed with Python libraries. For conducting cluster analysis, three main components have been identified that characterize the level of population involvement in SPVO studies, quality of life, and engagement in high-productivity industries, migration situation. As a result of the conducted analysis, seven clusters were formed, describing key characteristics determining the level of demand for SPVO. The results of the study systematically summarize the actual socio-economic situation in the regions and describe its influence on regional SPVO systems. They will be useful for executive bodies of Russian Federation subjects responsible for public administration in the sphere of education, federal executive authorities, and scientific institutes. A promising direction for applying the results of this study is optimizing control figures for admissions and adapting them to the socio-economic realities of regions.