<![CDATA[Technological advancements have made it easier for students to access information. However, many Computer Science students still struggle to determine a thesis specialization that aligns with their skills and interests. This study employs the K-Nearest Neighbor (KNN) algorithm to classify students' thesis specializations based on their academic data. The dataset consists of 100 students, with 80 used for training and 20 for testing. The KNN model was applied with parameters k=3k=3k=3 and k=5k=5k=5, generating predictions for thesis specializations such as Artificial Intelligence, Data Mining, and other fields. Model evaluation was conducted using accuracy, precision, recall, and confusion matrix metrics. The results show that the KNN model with k=3k=3k=3 achieved an accuracy of X%, precision of Y%, and recall of Z%. The implementation of KNN in this study demonstrated reasonably accurate results and can serve as a recommendation tool for students in selecting their thesis topics.]]>
Copyrights © 2025
