Analisis Analisis Prediksi Kelulusan Siswa Menggunakan Algoritma Gradient Boosting Berbasis Orange Data Mining

Deli Ananda Delin

doi:10.31004/riggs.v5i2.12588

Authors

Deli Ananda Delin Universitas HKBP Nommensen Pematangsiantar

DOI:

https://doi.org/10.31004/riggs.v5i2.12588

Keywords:

Gradient Boosting, Student Performance, Machine Learning, Orange Data Mining, Prediksi Kelulusan Siswa

Abstract

Prediksi kelulusan siswa merupakan salah satu penerapan Educational Data Mining yang dapat membantu institusi pendidikan dalam mengidentifikasi siswa yang berpotensi mengalami kesulitan akademik sejak dini. Informasi tersebut dapat digunakan sebagai dasar dalam pengambilan keputusan untuk memberikan pendampingan atau intervensi akademik yang lebih tepat sasaran. Penelitian ini bertujuan untuk membangun model prediksi kelulusan siswa menggunakan algoritma Gradient Boosting dengan memanfaatkan Student Performance Dataset. Proses penelitian dilakukan menggunakan aplikasi Orange Data Mining yang meliputi tahap prapemrosesan data, pembentukan model, dan evaluasi performa. Pada tahap prapemrosesan, atribut G3 ditransformasikan menjadi atribut kategorikal Target dengan dua kelas, yaitu Lulus dan Tidak Lulus, kemudian atribut G3 dipindahkan ke bagian Ignored untuk menghindari terjadinya data leakage. Model diuji menggunakan metode 5-Fold Cross Validation dan dievaluasi berdasarkan nilai Area Under Curve (AUC), Accuracy, Precision, Recall, F1-Score, Matthews Correlation Coefficient (MCC), serta Confusion Matrix. Hasil penelitian menunjukkan bahwa algoritma Gradient Boosting menghasilkan nilai AUC sebesar 0,969, Accuracy sebesar 89,6%, Precision sebesar 0,896, Recall sebesar 0,896, F1-Score sebesar 0,896, dan MCC sebesar 0,765. Hasil tersebut menunjukkan bahwa model memiliki kemampuan klasifikasi yang sangat baik dalam membedakan siswa yang termasuk kategori Lulus dan Tidak Lulus. Dengan demikian, algoritma Gradient Boosting dapat menjadi salah satu alternatif yang efektif untuk mendukung sistem prediksi kelulusan siswa dan membantu proses pengambilan keputusan di bidang pendidikan.

Downloads

Download data is not yet available.

References

[1] FAlwarthan, S., Alshahrani, A., & Alghamdi, A. (2022). Educational data mining and machine learning for student performance prediction: A review. Computational Intelligence and Neuroscience. https://doi.org/10.1155/2022/8924028

[2] Chaka, C. (2022). Machine learning and educational data mining in student performance prediction: A systematic review. Journal of e-Learning and Knowledge Society, 18(3), 1–15.

[3] Dabhade, P., Agarwal, R., Alameen, K. P., Fathima, A. T., Sridharan, R., & Gopakumar, G. (2021). Educational data mining for predicting students’ academic performance using machine learning algorithms. Materials Today: Proceedings, 47, 5260–5267. https://doi.org/10.1016/j.matpr.2021.05.646

[4] Gerlache, H. A. M., Moreno Ger, P., & de la Fuente Valentín, L. (2021). Towards the grade's prediction: A study of different machine learning approaches to predict grades from student interaction data. International Journal of Interactive Multimedia and Artificial Intelligence. https://doi.org/10.9781/ijimai.2021.11.007

[5] Handayani, L., & Priyadi. (2025). A machine learning-based early warning system for student performance prediction: System development and empirical evaluation in higher education. Journal of Artificial Intelligence in Information Technology. https://doi.org/10.51903/92j5wj58

[6] Li, S., & Liu, T. (2021). Performance prediction for higher education students using deep learning. Complexity, 2021, Article ID 9958203. https://doi.org/10.1155/2021/9958203

[7] Orji, F. A., & Vassileva, J. (2022). Machine learning approach for predicting students’ academic performance and study strategies based on their motivation. arXiv. https://doi.org/10.48550/arXiv.2210.08186

[8] P. S., A. T., & D. D. (2021). Student performance prediction using machine learning. Advances in Parallel Computing Technologies and Applications. https://doi.org/10.3233/APC210137

[9] Roslan, M. H., & Chen, C. J. (2022). Educational data mining for student performance prediction: A systematic literature review (2015–2021). International Journal of Emerging Technologies in Learning (iJET), 17(5), 147–179. https://doi.org/10.3991/ijet.v17i05.27685

[10] Trakunphutthirak, R., & Lee, V. C. S. (2022). Application of educational data mining approach for student academic performance prediction using progressive temporal data. Journal of Educational Computing Research, 60(3), 742–776. https://doi.org/10.1177/07356331211048777

[11] Xiao, Y., Ji, M., & Hu, Y. (2022). Machine learning-based prediction models for student academic performance: A systematic review. Engineering Reports. https://doi.org/10.1002/eng2.12482

[12] Xiong, Z., Li, H., Liu, Z., Chen, Z., Zhou, H., Rong, W., & Ouyang, Y. (2024). A review of data mining in personalized education: Current trends and future prospects. arXiv. https://doi.org/10.48550/arXiv.2401.08774

[13] Zhang, Y., Yun, Y., An, R., Cui, J., Dai, H., & Shang, X. (2021). Educational data mining techniques for student performance prediction: Method review and comparison analysis. Frontiers in Psychology, 12, 698490. https://doi.org/10.3389/fpsyg.2021.698490

[14] Pan, J., Zhao, Z., & Han, D. (2025). Academic performance prediction using machine learning approaches: A survey. IEEE Transactions on Learning Technologies, 18, 351–368. https://doi.org/10.1109/TLT.2025.3554174

[15] Jain, A., Sharma, P., & Singh, R. (2022). Academic performance prediction using machine learning: A comprehensive and systematic review. Proceedings of the 2022 International Conference on Electronic Systems and Intelligent Computing (ICESIC). https://doi.org/10.1109/ICESIC53714.2022.9783512