Application of Machine Learning for Student Data Classification

Penerapan Machine Learning untuk Klasifikasi Data Siswa

Abstract

Student data classification plays an important role in academic analysis, helping schools find patterns, organize student information, and guide decisions about how well students are doing and how to improve programs. As more educational data becomes available, machine learning offers better and more reliable ways to understand student traits and predict how they will perform in learning. This study uses machine learning to sort student data based on key academic and personal details. The research process covers cleaning the data, choosing the best features to use, and testing three different algorithms: Naïve Bayes, K-Nearest Neighbors (KNN), and Decision Tree. The effectiveness of these methods is measured using accuracy, precision, recall, and F1-score. The results show that the Decision Tree method is the most accurate at sorting student data, followed by KNN and Naïve Bayes. These results highlight how useful machine learning can be in the field of educational data mining, especially for keeping track of student progress, spotting students who might struggle early on, and helping schools make better decisions. This study offers real-world advice for schools looking to use data more effectively in managing students and planning educational programs.