Analisis Komparatif Model Regresi Machine Learning untuk Prediksi Prestasi Akademik Siswa dengan Optimasi Hyperparameter
DOI:
https://doi.org/10.30865/jurikom.v12i6.9240Keywords:
Prediksi Prestasi Akademik, CatBoost, Gradient Boosting, Optimasi, Hyperparameter, Machine LearningAbstract
Low accuracy in the early identification of at-risk students often hinders timely academic intervention. This study analyzes and compares seven machine learning algorithms to predict student academic achievement, aiming to provide a foundation for a reliable early warning model. The dataset includes 2.392 students with 15 features covering demographics, learning behavior, and environmental support. Model training was performed using GridSearchCV optimization combined with stratified cross-validation to mitigate overfitting.Performance was evaluated using MAE, RMSE, and R². The results show CatBoost performed the best R² = 0,774; RMSE = 0,581; MAE = 0,306) followed by LightGBM (R² = 0,771) and Gradient Boosting (R² = 0,767), while MLP showed the lowest performance. Feature importance analysis placed GPA as the dominant predictor, followed by absenteeism and weekly study time. These findings affirm the superiority of boosting-based models in capturing complex nonlinear relationships and provide a practical framework for educational institutions to build data-driven early warning systems.
References
[1] T. Nabillah and A. P. Abadi, “Faktor penyebab rendahnya hasil belajar siswa,” Pros. Semin. Nas. Mat. dan Pendidik. Mat. Sesiomadika, vol. 2, no. 1c, pp. 659–663, 2019, [Online]. Available: http://journal.unsika.ac.id/index.php/sesiomadika
[2] D. L. Kusumaningrini and N. Sudibjo, “Faktor-Faktor Yang Mempengaruhi Motivasi Belajar Siswa Di Era Pandemi Covid-19,” Akademika, vol. 10, no. 01, pp. 145–161, 2021, doi: 10.34005/akademika.v10i01.1271.
[3] A. Mahmudi, J. Sulianto, and I. Listyarini, “Hubungan Perhatian Orang Tua Terhadap Hasil Belajar Kognitif Siswa,” J. Pedagog. dan Pembelajaran, vol. 3, no. 1, p. 122, 2020, doi: 10.23887/jp2.v3i1.24435.
[4] R. I. Nurachim, “Pemilihan Model Prediksi Indeks Harga Saham Yang Dikembangkan Berdasarkan Algoritma Support Vector Machine(Svm) Atau Multilayer Perceptron(Mlp) Studi Kasus : Saham Pt Telekomunikasi Indonesia Tbk,” J. Teknol. Inform. dan Komput., vol. 5, no. 1, pp. 29–35, 2019, doi: 10.37012/jtik.v5i1.243.
[5] B. Prasojo and E. Haryatmi, “Analisa Prediksi Kelayakan Pemberian Kredit Pinjaman dengan Metode Random Forest,” J. Nas. Teknol. dan Sist. Inf., vol. 7, no. 2, pp. 79–89, 2021, doi: 10.25077/teknosi.v7i2.2021.79-89.
[6] F. A. Rangkuti, S. Sundari, T. Informatika, and U. H. Medan, “Implementasi Gradient Boosting Machines Untuk Prediksi Harga Implementation Of Gradient Boosting Machines For House Price Prediction In South Jakarta,” vol. 4, no. 2, pp. 164–172, 2025.
[7] N. K. C. PRATIWI, N. IBRAHIM, and S. SAIDAH, “Prediksi Kanker Paru menggunakan Grid search untuk Optimasi Hyperparameter pada Algoritma MLP dan Logistic Regression,” ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 12, no. 3, p. 556, 2024, doi: 10.26760/elkomika.v12i3.556.
[8] B. Sunarko et al., “Penerapan Stacking Ensemble Learning untuk Klasifikasi Efek Kesehatan Akibat Pencemaran Udara,” Edu Komputika J., vol. 10, no. 1, pp. 55–63, 2023, doi: 10.15294/edukomputika.v10i1.72080.
[9] T. A. E. Putri, T. Widiharih, and R. Santoso, “Penerapan Tuning Hyperparameter Randomsearchcv Pada Adaptive Boosting Untuk Prediksi Kelangsungan Hidup Pasien Gagal Jantung,” J. Gaussian, vol. 11, no. 3, pp. 397–406, 2023, doi: 10.14710/j.gauss.11.3.397-406.
[10] A. Hadianto and W. H. Utomo, “CatBoost Optimization Using Recursive Feature Elimination,” vol. 9, no. 2, pp. 169–178, 2024, doi: 10.15575/join.v9i1.1324.
[11] T. S. Wibawa, N. K. Ningrum, and A. Syahreza, “Comparison of CatBoost and LightGBM Models for Air Humidity Prediction,” vol. 9, no. 3, pp. 803–809, 2025.
[12] D. Kedalaman and P. Ea, “Prediksi Magnitudo Gempa Menggunakan Random Forest , Support Vector Regression , XGBoost , LightGBM , dan Multi-Layer Perceptron Berdasarkan Prediksi Magnitudo Gempa Menggunakan Random Forest , Support Vector Regression , XGBoost , LightGBM , dan Multi-La,” no. December, 2024, doi: 10.52436/1.jpti.470.
[13] D. Ananda, A. Pertiwi, and M. A. Muslim, “Prediksi Rating Aplikasi Playstore Menggunakan Xgboost Prediksi Rating Aplikasi Playstore Menggunakan Xgboost,” ResearchGate, no. October 2020, p. 6, 2022.
[14] Y. Dasril, M. Aziz, M. F. Al, and B. Prasetiyo, “Credit Risk Assessment in P2P Lending Using LightGBM and Particle Swarm Optimization,” vol. 9, no. January, pp. 18–28, 2023.
[15] J. T. Hancock and T. M. Khoshgoftaar, “CatBoost for big data : an interdisciplinary review,” J. Big Data, 2020, doi: 10.1186/s40537-020-00369-8.
[16] E. Fitri, “Journal Of Applied Computer Science And Technology ( JACOST ) Analisis Perbandingan Metode Regresi Linier , Random Forest Regression dan Gradient Boosted Trees Regression Method untuk Prediksi Harga Rumah,” vol. 4, no. 1, pp. 58–64, 2023.
[17] W. Indrasari and H. Suhendar, “Analisis Model Prediksi Cuaca Menggunakan Support Vector Machine , Gradient Boosting , Random Forest , DAN,” vol. XII, pp. 119–128, 2024.
[18] A. S. Firdan and D. Kurniadi, “Proyek Kontruksi Jalan Menggunakan Metode Backpropagation Dengan Model MLP ( Studi Kasus : Jalan Wilayah Kabupaten PekalongaN ),” vol. 2, no. 4, pp. 1–12, 2025.
[19] N. O. Syamsiah and I. Purwandani, “Penerapan Ensemble Stacking untuk Peramalan Laba Bersih Bank Syariah Indonesia (BSI),” Build. Informatics, Technol. Sci., vol. 3, no. 3, pp. 295–301, 2021, doi: 10.47065/bits.v3i3.1017.
[20] A. Primajaya and B. N. Sari, “Random Forest Algorithm for Prediction of Precipitation,” Indones. J. Artif. Intell. Data Min., vol. 1, no. 1, p. 27, 2018, doi: 10.24014/ijaidm.v1i1.4903.
[21] G. Arther Sandag, “Prediksi Rating Aplikasi App Store Menggunakan Algoritma Random Forest,” Cogito Smart J. |, vol. 6, no. 2, pp. 167–178, 2020.
