<![CDATA[Abstract College students often experience academic, social, and personal stress that can lead to mental health issues such as depression. If left untreated, this condition can disrupt academic achievement and social relationships, and even trigger extreme behavior. This study aims to design and develop a system to predict the risk of depression in college students using the K-Nearest Neighbor (KNN) classification algorithm. Data were collected from 300 students through a Likert-scale questionnaire. The system was developed using Python for pre-processing. The analysis process included data selection, cleaning, transformation, classification with KNN, and performance evaluation using a confusion matrix. Testing of 60 test data sets yielded 85% accuracy, 90% precision, and 83% recall. This system has the potential to be used as an early detection tool for students and educational institutions. Keywords : Depression, Students, K-Nearest Neighbor, Classification, Data Mining]]>
Copyrights © 2025
