<![CDATA[The prediction of student graduation has become an essential component in academic performance analysis, especially in identifying factors that influence student success. This study aims to develop a simple prediction model for student graduation status using the K-Nearest Neighbor (KNN) algorithm. The dataset used consists of student academic records, including Grade Point Average (GPA) and total completed credits (SKS). The data were processed and divided into training and testing sets to evaluate the model’s performance. The KNN algorithm was applied with various K values (1, 3, 5, 7, and 9) to determine the most optimal classification result. The experiment showed that the KNN model achieved the highest accuracy of 90% when K=3, indicating that the algorithm performs effectively in classifying students based on academic achievement. The results suggest that KNN can be utilized as an initial analytical tool for predicting student graduation likelihood, which can later support decision-making in academic management systems.]]>
Copyrights © 2025
