Prediksi Kelulusan Mahasiswa Menggunakan Algoritma Decision Tree C4.5 Berbasis Data Akademik dengan Validasi 10-Fold

Nurhasanah, Nurhasanah
Setiyawan, Risky Dwi
Hermawan, Doni
Herdiyanto, Oki

TIN: TERAPAN INFORMATIKA NUSANTARA
Vol 6 No 6 (2025): November 2025

Predicting student graduation outcomes is an important indicator for evaluating academic quality and the effectiveness of learning processes in higher education. This study aims to analyze and predict student graduation status based on academic data using the C4.5 Decision Tree algorithm. The dataset consists of 100 students from the Informatics Study Program at Universitas Pamulang, with five main attributes: Grade Point Average (GPA), attendance percentage, assignment scores, midterm examination scores, and final examination scores. The research stages include data cleaning, data transformation, model construction, and model evaluation using the 10-fold cross-validation technique to ensure performance stability. The experimental results show an accuracy of 88.74%, precision of 91.79%, recall of 95.34%, and an AUC value of 0.94, indicating that the model demonstrates strong discriminatory ability in classifying graduation outcomes. GPA and final examination scores were identified as the most influential attributes in determining graduation predictions. The resulting predictive model is expected to serve as a foundation for developing an early warning system that enables universities to identify at-risk students and support data-driven decision-making to improve educational quality.