Evaluasi Kinerja Algoritma Klasifikasi dalam Studi Kasus Prediksi Kelulusan di Universitas XYZ

Abstract

This study aims to evaluate the performance of three classification algorithms—Decision Tree, K-Nearest Neighbors (KNN), and Naive Bayes—in a case study of predicting student graduation outcomes at XYZ University. Utilizing a dataset that includes a diverse range of academic attributes of students, this research conducts an in-depth analysis of each algorithm's capability to predict students' graduation status. The findings reveal that the Decision Tree provides the best performance with an accuracy rate of 97%, while KNN also shows very good results with similar accuracy, and Naive Bayes records an accuracy of 91%. The advantage of the Decision Tree lies in its ease of interpretation and high decision transparency, making it highly suitable for educational system implementations. Meanwhile, KNN excels in handling complex datasets due to its adaptability to data variability, and Naive Bayes offers rapid analysis speeds ideal for processing large data volumes. These insights provide valuable guidance for educational institutions in developing more effective graduation prediction systems and supporting strategic decisions in academic management. The study also opens avenues for further research in exploring these algorithms' applications in broader educational contexts, as well as fine-tuning modeling techniques to enhance prediction accuracy and efficiency.