MACHINE LEARNING ALGORITHMS FOR IDENTIFYING YOUTH INTERESTS AND DEVELOPING A SOFTWARE FRAMEWORK

Abstract

The rapid development of digital technologies and data-driven decision-making has significantly expanded the possibilities for understanding the interests and preferences of young people. In pedagogical universities, especially within information and communication technology programs, there is a growing need for analytical tools that can process large volumes of heterogeneous data related to learners’ behavior, educational choices, and digital activities. This study explores the application of machine learning algorithms for identifying youth interests and the development of a corresponding software framework that supports analytical and educational tasks. The relevance of the research is determined by the increasing role of personalized learning, career guidance, and data-informed educational management. The paper focuses on the conceptual foundations of interest identification, the selection and adaptation of machine learning algorithms, and the integration of these algorithms into a unified software framework suitable for educational contexts. The results demonstrate that machine learning-based analysis enables more accurate and dynamic identification of youth interests compared to traditional survey-based methods, thereby contributing to more effective pedagogical planning and student support.