Abstract
Academic achievement is a measure of students' learning outcomes, encompassing aspects of knowledge and skills. Academic performance serves as a crucial indicator in evaluating students' learning progress. MAS Al-Wasliyah Petatal is committed to providing quality education but still faces limitations in applying technology to evaluate student learning. The current evaluation process relies on teachers' subjective assessments, which restricts the information about students' progress. Therefore, the implementation of machine learning is proposed as a solution to enhance objectivity in student learning evaluation through more effective data processing. The method used is the K-Means Clustering algorithm, which can group or classify data based on specific patterns. This study aims to evaluate the extent to which machine learning can process student learning evaluation data through the analysis results obtained from the clustering process, which are then used as benchmarks to improve the evaluation system and provide feedback for students needing improvement in their academic performance. The data used comprises students' grades from the odd semester of the 2024/2025 academic year, with a total of 210 data points. The clustering results produced three clusters: the "good" cluster with 60 students, the "average" cluster with 99 students, and the "low" cluster with 51 students.
