A Comparative Analysis of Machine Learning Algorithms for Predicting Student Academic Success and Graduation: A Feature Importance Analysis

Abstrak

Student academic success and graduation are important indicators for evaluating the quality of higher education. The ability to identify students at risk of academic failure or dropout at an early stage can help universities implement appropriate intervention strategies. This study aims to compare the performance of several machine learning algorithms in predicting student academic success and graduation and to identify the most influential factors affecting prediction outcomes through feature importance analysis. The dataset used in this study was the Predict Students' Dropout and Academic Success dataset obtained from Kaggle. Four machine learning algorithms were employed, namely Decision Tree, Random Forest, Support Vector Machine (SVM), and XGBoost. Model performance was evaluated using Accuracy, Precision, Recall, and F1-Score metrics. The results showed that Random Forest and XGBoost achieved the highest accuracy of 91.05%. However, Random Forest demonstrated the best overall performance with a Precision of 89.19%, Recall of 97.06%, and F1-Score of 92.96%. Feature importance analysis revealed that Curricular units 2nd sem (approved), Curricular units 1st sem (approved), and Curricular units 2nd sem (grade) were the most influential factors in predicting student academic success and graduation. The findings indicate that machine learning can be effectively utilized to support the development of early warning systems in higher education institutions to improve student academic outcomes. Keywords: Machine Learning, Student Academic Success, Graduation Prediction, Random Forest, Feature Importance Analysis, Educational Data Mining

Kata Kunci