ARCHITECTURE OF EDUCATIONAL ANALYTICS INFORMATION TECHNOLOGY USING DATA MINING METHODS

Abstract

The article explores approaches to designing the architecture of educational analytics information technology with the integration of data mining methods. A conceptual model of an analytical system is proposed, enabling the identification of relationships between student activity in the learning environment and their academic performance, as well as the detection of temporal attendance patterns. The application of cluster analysis made it possible to distinguish typical behavioral groups of students, opening prospects for personalized learning and early risk detection. The research results can be used to develop effective decision support systems in higher education institutions.Purpose of the Study. To develop a conceptual architecture of educational analytics information technology that integrates data mining methods to identify hidden patterns in student behavior, predict academic performance, and support decision- making in higher education. Special attention is paid to the application of machine learning algorithms, cluster analysis, regression modeling, and data visualization in the context of building an effective, scalable, and adaptive analytical system.Methodology. The methodological basis of the study is an interdisciplinary approach that combines the principles of educational analytics, data mining, and information systems architecture design. Scientific Novelty. The scientific novelty of the study lies in the integration of visualization, forecasting, and decision support modules into a unified architecture tailored to the needs of higher education institutions, as well as in the practical validation of the model using real LMS data, which confirms its effectiveness and adaptability to the conditions of the modern educational environment.Conclusions It has been proven that the development of information technologies based on data mining methods in the implementation of e-learning systems contributes to solving tasks related to understanding student behavior, improving the quality of online courses, enhancing teaching methods, reducing the cost of organizing the learning process, and defining future directions for educational analytics in line with global trends.