<![CDATA[Improving the quality of education requires an objective, systematic, and data-driven academic performance assessment system. One technological approach that can be used to support this is data mining, specifically the K-Means Clustering method. This studyaims to cluster student academic data based on report card grades for the odd semester of the 2024/2025 academic year using the K-Means algorithm. Data processing was performed using RapidMiner software, with the optimal number of clusters selected at three (K=3) based on the Davies Bouldin Index (DBI) of 0.077. The clustering results form three main categories: Cluster 0 contains 174 students with average academic performance, Cluster 1 contains only one student with the lowest performance, and Cluster 2 contains 107 students with high academic performance. This grouping provides more structured and useful information for schools in designing targeted academic development strategies. This study demonstrates the effectiveness of the K-Means Clustering method in identifying student academic patterns and classifications.]]>
Copyrights © 2025
