Application of Econometric Methods for Human Capital Management

Abstract

The study analyzes the use of econometric methods to optimize human capital management. The study aims to combine various econometric methods into a step-by-step algorithm to improve the human capital management system. The methodological basis of the study was the principal component analysis (PCA), cluster analysis using the K-means method, and linear discriminant analysis (LDA). Testing of the selected methods was implemented using the Python programming language. Enterprises from the Eurasian Economic Union (EAEU) countries were selected as test objects; the total sample for selected enterprises amounted to 200 observations for 15 indicators characterizing human capital. Using PCA to reduce data dimensionality simplified a complex data set, making it more manageable for identifying critical areas of variability in aspects of human capital. Testing showed that the four principal components explained about 78.7% of the variance in the data. Using K-means allowed the data to be grouped into four separate clusters that identified different groups of employees with specific characteristics. The application of LDA helped to identify the key factors separating the clusters. Testing showed that the first and second discriminant components effectively separated the clusters, explaining a significant portion of the variance between them (78.7% of explained variance). The study results demonstrate the importance of using econometric methods in the actual practice of human capital management, offering new approaches and tools for increasing the efficiency of management decisions in the context of accelerating the intellectual development of economic systems.