MODERN APPROACHES TO PERSONALIZED LEARNING IN HIGHER TECHNICAL EDUCATION

Abstract

The digitalization of higher technical education has significantly increased the volume of educational data generated by learning management systems, student information systems, digital assessment environments, communication platforms, and learning analytics tools. However, learner-related information remains fragmented across multiple independent systems, limiting opportunities for evidence-informed pedagogical decision-making and personalized learning. The purpose of this study is to develop a conceptual approach to personalized learning by designing a personalized learning profile as an integrated component of a digital educational ecosystem. The research is based on the analysis and synthesis of contemporary studies in digital pedagogy, learning analytics, educational data mining, personalized learning, and artificial intelligence in education, together with conceptual modelling methods. The proposed personalized learning profile integrates heterogeneous educational data, including academic achievements, competency development, learning engagement, educational interactions, and behavioural indicators, learning preferences, and feedback history into a coherent and continuously evolving pedagogical representation of the learner. Acting as an integrated knowledge base within the digital educational ecosystem, the profile enables AI-assisted analysis of learner data to generate personalized recommendations, identify learning needs, support adaptive learning pathways, and facilitate evidence-informed pedagogical decision-making. Unlike conventional student information systems that primarily accumulate administrative records, the proposed model provides a learner-centred framework supporting adaptive learning, competency monitoring, learning analytics, and evidence-informed educational decision-making. The conceptual model contributes to the theoretical development of digital pedagogy by demonstrating how integrated learner data can support personalized educational pathways and lifelong professional development within higher technical education. The practical significance of the study lies in providing a methodological foundation for designing digital educational ecosystems that support intelligent educational services and improve the quality of professional training.