<![CDATA[Student productivity is influenced by various factors, including academic habits, lifestyle characteristics, and digital distraction behaviors. The increasing use of digital technologies, such as smartphones, social media, and online gaming, has created new challenges for maintaining student focus and academic performance. Therefore, understanding and predicting student productivity levels is important for supporting effective educational management and student success. This study aims to classify student productivity levels using machine learning techniques based on academic, behavioral, and digital distraction variables. The study utilized the Student Productivity & Digital Distraction Dataset obtained from Kaggle, consisting of 20,000 student records. The productivity score was transformed into five productivity categories, namely very low, low, medium, high, and very high productivity. Four machine learning algorithms, including Decision Tree (DT), and K-Nearest Neighbors (KNN), Gradient Boosting (GB), and Random Forest (RF) were evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. The results showed that RF achieved the best performance with an accuracy of 81.15%, precision of 81.35%, recall of 81.15%, and F1-score of 81.23%, outperforming GB, DT, and KNN. The findings indicate that ensemble learning methods are more effective in modeling the complex relationships among academic habits, lifestyle factors, digital distraction, and student productivity. Furthermore, the study demonstrates the potential of machine learning as a decision-support tool for educational management, enabling the identification of students with different productivity levels and supporting data-driven interventions to improve academic outcomes.]]>
