Optimizing Hybrid Learning Outcomes via Clustering-Guided Data Mining Techniques in Higher Education

Higher education has adopted hybrid learning models more quickly in recent years, which calls for creative ways to maximize learning results. This study offers a novel approach for improving the efficacy of hybrid learning environments by incorporating clustering-guided data mining techniques. We use clustering methods like K-Means, DBSCAN, and Hierarchical Clustering to divide up students into groups according to their learning styles and degrees of engagement after examining large datasets of student interactions, behaviors, and performance indicators. For different learner profiles, these clusters are then utilized to tailor instructional tactics, materials, and feedback. Through a combination of quantitative and qualitative studies, the study further investigates how these customized techniques affect student happiness, performance, and retention. Compared to conventional one-size-fits-all teaching strategies, experimental results show that clustering-guided approaches dramatically increase learning outcomes. In addition to offering practical advice for educators and institutions looking to optimize the effectiveness of blended learning models, this study highlights the promise of data-driven personalization in hybrid education.