Machine Learning-Based Optimization of Learning Strategies for Enhanced Student Performance

The integration of machine learning into education offers new opportunities to optimize learning strategies through data-driven personalization. This study aims to predict students’ academic performance and identify key learning factors that can be leveraged to enhance individualized learning outcomes. A dataset containing 6,607 records and 19 predictor variables representing academic, behavioral, social, and environmental aspects was analyzed using three machine learning algorithms: Random Forest, XGBoost, and Artificial Neural Network. Model performance was evaluated using R-squared (R²), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The results indicate that XGBoost outperformed the other models, achieving an  and RMSE = 3.85, demonstrating superior predictive accuracy and model stability. Feature importance analysis revealed that attendance, study hours, parental involvement, and access to resources were the most influential predictors of student achievement. Furthermore, K-Means clustering identified three distinct learning profiles characterized by differences in motivation, engagement, and access to educational resources. These findings emphasize the potential of machine learning to support adaptive learning systems that provide personalized recommendations through Learning Management Systems (LMS). Future work should explore the integration of Explainable AI (XAI) techniques to improve model interpretability and conduct cross-context validation to ensure broader applicability across diverse educational settings.