<![CDATA[The selection of a study concentration is an important stage in a student’s academic journey, as it determines the direction of expertise to be pursued. However, many students experience difficulties in choosing a concentration that aligns with their abilities and interests. This study aims to develop a recommendation system for selecting concentrations for students of the Informatics Study Program using the K-Nearest Neighbor (KNN) algorithm. The data used consist of students’ academic scores from semesters 1 to 4, totaling 446 records. The classification process was carried out by dividing the data into 80% training data and 20% testing data. The experimental results indicate that the KNN model with k = 15 achieved the best accuracy of 74.44%. These results show that the KNN method is sufficiently effective in providing concentration recommendations, namely Web and Mobile (WEM) and Intelligent Systems (SCR), based on similarities in students’ academic score patterns. This system is expected to assist students in selecting appropriate concentrations and to serve as a decision-support tool for the study program in academic decision-making.]]>
Copyrights © 2026
