Klasifikasi Prestasi Akademik Mahasiswa Menggunakan Metode Random Forest

Classification of Student Academic Achievement Using Random Forest Method

Abstract

Student academic achievement is the main indicator in evaluating the quality of higher education. This study aims to classify student academic achievement using the Random Forest algorithm by utilizing academic data such as mid-term exam scores, final exam scores, assignments, attendance, notes, and final grades. The methods used include data collection from Kaggle, data preprocessing, data sharing, model training using Random Forest, and model performance evaluation. The results showed that the Random Forest model was able to classify student academic achievement with a high accuracy of 98.2%. Further analysis revealed that mid-term exam scores and final exam scores were the dominant factors in influencing the prediction of students' final grades. The conclusion of this study shows that the Random Forest algorithm is an effective tool in analyzing student academic data because it is able to provide accurate classification results and provide important insights for educational institutions to improve the quality of learning