<![CDATA[Improving the quality of education is one of the main priorities in managing academic institutions in the modern era. This effort is not only achieved through the improvement of facilities and infrastructure but also through the utilization of informationtechnology to analyze academic data more comprehensively. One approach that can be applied to understand patterns of student achievement is data mining, which is the process of extracting meaningful information from large datasets to identify relevant patterns and relationships. This study aims to implement the K-Means Clustering method in the data mining process to classify students based on their levels of academic achievement. The K-Means Clustering method was selected because of its ability to efficiently group data based on the similarity of individual students' academic scores. Through this method, student scores from various subjects are analyzed and grouped into several categories, such as high, medium, and low academic achievement. Theresearch stages include data collection, data cleaning and normalization, implementation of the K-Means algorithm, andevaluation of the clustering results. The results of this study are expected to provide a clearer overview of the distribution ofstudents' academic achievement within the school environment. The information obtained can be utilized as a basis for strategic decision-making, such as designing more effective learning programs, providing specialized guidance for students with low achievement, and increasing motivation among high-achieving students. Therefore, this study is expected to make ameaningful contribution to the application of data mining technology in supporting data-driven educational quality improvement and promoting the optimal development of students' potential.]]>
Copyrights © 2026
