Optimization of Personalized Digital Learning Trajectories of Students in Higher Education Based on Artificial Intelligence and Cluster Approach

Аннотация

This study investigates the optimization of personalized digital learning trajectories in higher education through
the integration of Artificial Intelligence (AI) and clustering approaches. The rapid digital transformation of education
requires adaptive systems capable of analyzing students’ learning behaviors and academic performance in real time.
In this research, machine learning techniques, including clustering algorithms (K-means and hierarchical clustering) and
predictive models (regression and classification), were applied to develop an adaptive learning framework. The results
demonstrate that the proposed AI-based model improves the accuracy of learning outcome predictions and enhances
students’ academic performance compared to traditional learning systems. The findings confirm that AI-driven clustering
significantly enhances personalization, learning efficiency, and decision-making in educational environments.