<![CDATA[This study explores the application of machine learning techniques to predict student achievement based on study habits, parental involvement, and school environment. Using a dataset from Kaggle comprising academic, behavioral, and contextual variables, four machine learning algorithms, namely K-Nearest Neighbors (KNN), Naïve Bayes, Support Vector Machine (SVM), and Random Forest, were implemented and evaluated. Model performance was evaluated using accuracy, precision, recall, F1-score, ROC curve, and Precision–Recall curves. Results show that all models effectively classified students into low- and high-achievement categories, with SVM achieving the highest accuracy (94.02%) and the strongest overall performance. The findings highlight the potential of machine learning-driven predictive analytics in educational settings, enabling early identification of at-risk students and supporting evidence-based interventions. By integrating diverse factors influencing academic performance, this study demonstrates how data-driven approaches can enhance educational management, inform policy, and promote equitable learning outcomes.]]>
Copyrights © 2025
