<![CDATA[The rapid growth of e-learning platforms has intensified the need for effective personalization mechanisms to address content overload and diverse learner characteristics. Recommendation systems based on data mining have emerged as essential components for guiding learners toward relevant courses and adaptive learning paths. This study aims to design and develop an integrated data mining-based recommendation system for e-learning that enhances personalization and learning effectiveness within a unified platform architecture. This research adopts a research and development approach combined with system engineering methodology. Learner interaction data, course metadata, and performance records were collected from the e-learning platform and processed through data preprocessing techniques, including cleaning, feature extraction, and clustering. The recommendation engine integrates collaborative filtering, content-based filtering, and reinforcement learning for adaptive learning path optimization. System performance was evaluated using accuracy, precision, recall, F1-score, MAE, and NDCG metrics. The results show significant improvements compared to the baseline model, including higher recommendation accuracy and a substantial increase in learner completion rates. The discussion confirms that hybrid modeling and integrated system architecture enhance both algorithmic performance and pedagogical outcomes. In conclusion, the proposed system provides a scalable and effective framework for personalized e-learning through integrated data mining techniques.]]>
Copyrights © 2026
