<![CDATA[With the proliferation of digital learning platforms—including Learning Management Systems (LMS)—data on student learning activities has been generated that is useful for supporting the evaluation of student learning. A total of 200 data points were analyzed, with key variables including login frequency, study duration, quiz scores, assignment scores, timeliness in submitting assignments, attendance, and engagement during learning. These variables can be analyzed using machine learning to predict students’ comprehension levels early on, enabling teachers to identify which students require additional support. This study focuses on the application of machine learning to predict students’ comprehension levels at SMP Negeri 18 Padang as an effort to support more accurate decision-making in the learning process. This study utilized three algorithms: Random Forest, Decision Tree, and Naïve Bayes. The results of the testing revealed that the Decision Tree algorithm achieved the highest accuracy rate at 88.52%, followed by the Random Forest algorithm at 83.61%, and the Naïve Bayes algorithm at 62.30%. Of the three algorithms, the Decision Tree algorithm achieved the highest accuracy. This algorithm can be utilized as an early warning system for teachers to identify which students have high, moderate, or low levels of understanding, allowing teachers to provide appropriate support.]]>
Copyrights © 2026
