Prediksi Performa Akademik Siswa Berdasarkan Kehadiran dan Aktivitas E-Learning Menggunakan Algoritma Decision Tree

Abstract

The advancement of digital technology has driven the widespread adoption of e-learning systems in the field of education. However, a key challenge lies in effectively utilizing e-learning data to improve students' academic performance. This study aims to predict students' academic performance based on their attendance and activity data within an e-learning platform using the Decision Tree algorithm. The dataset used was obtained from the public platform Kaggle, titled “Student’s Academic Performance Dataset”, which includes demographic attributes, attendance records, and student engagement in online learning. The analysis process involved data preprocessing, model training, and performance evaluation using metrics such as accuracy, precision, recall, F1-score, and cross-validation. The results show that the combination of attendance and e-learning activity has a significant correlation with academic performance, with the model achieving an accuracy of 78.12% and an F1-score of 0.77. These findings highlight the potential of utilizing learning analytics to support data-driven academic decision-making and provide early interventions for at-risk students.