Optimasi Kinerja Algoritma Random Forest dengan SMOTE untuk Prediksi Kinerja Akademik Siswa
DOI:
https://doi.org/10.47065/jimat.v6i2.950Keywords:
Random Forest; SMOTE; Feature Engineering; Student Performance; Educational Data MiningAbstract
Student academic performance prediction is an essential component of Educational Data Mining (EDM) for the early identification of at-risk students. This approach aims to improve prediction accuracy and support decision-making for the early identification of at-risk students. This study proposes an optimized prediction pipeline that integrates feature engineering, Pearson Correlation-based Feature Filtering (PCFF), the Synthetic Minority Over-sampling Technique (SMOTE), and Random Forest (RF) to predict student academic performance. The Portuguese Student Performance Dataset (1,043 clean records; Pass = 814, Fail = 230) was used for evaluation. Four engineered features were constructed, reducing the feature space to 15 features through PCFF (threshold |r| ? 0.1). SMOTE was applied exclusively within each training fold to prevent data leakage. Two primary models were evaluated: a baseline Naïve Bayes model (Accuracy = 90.43%) and the proposed RF Default + SMOTE model (Accuracy = 93.78%, Recall = 95.09%, F1-score = 95.98%). Ten-fold stratified cross-validation achieved an accuracy of 90.89% ± 2.08%. The engineered feature G_avg obtained the highest feature importance score (0.285), outperforming the original grade features. The results demonstrate that integrating SMOTE and feature engineering significantly improves minority class detection, reducing False Negatives from 15 (baseline) to 8 (RF + SMOTE), representing a 46.7% improvement in identifying at-risk students.
Downloads
References
K. P. Pengkomputeran, I. Media, and T. Mara, “Student Dropout Prediction Using Random Forest and XGBoost Method,” INTENSIF, vol. 9, no. 1, pp. 147–157, 2025, doi: DOI: https://doi.org/10.29407/intensif.v9i1.21191.
R. A. Azizah, F. A. Bachtiar, S. Adinugroho, U. Brawijaya, and P. Korespondensi, “Klasifikasi Kinerja Akademik Siswa Menggunakan Neighbor Weighted K-Nearest Neighbor Dengan Seleksi Fitur Information Classification Of Student Academic Performance Using Neighbor Weighted K-Nearest Neighbor With Information Gain As,” J. Teknol. Inf. dan Ilmu Komput., vol. 9, no. 3, pp. 605–614, 2022, doi: 10.25126/jtiik.202295751.
I. Riadi et al., “Prediksi Kelulusan Tepat Waktu Berdasarkan Riwayat Akademik Menggunakan Metode K-Nearest Neighbor Predicted Timely Graduation Based On Academic History Before College With K-Nearest Neighbor Method,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 2, pp. 249–256, 2024, doi: 10.25126/jtiik.20241127330.
E. P. Saputra et al., “Komparasi Machine Learning Berbasis Pso Untuk Prediksi Tingkat Keberhasilan Belajar Berbasis E-Learning Comparation Of Pso-Based Learning Machine For E-Learning-Based,” J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 2, pp. 321–328, 2023, doi: 10.25126/jtiik.2023106469.
U. Kristen, K. Wacana, and J. Barat, “Prediksi Mahasiswa Drop-Out Di Universitas Xyz Prediction Of Student Drop-Out At Xyz University,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 6, pp. 1345–1350, 2024, doi: 10.25126/jtiik.2024118689.
C. C. F. Selection, “Comparing Correlation-Based Feature Selection and Symmetrical,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 158, pp. 542–554, 2026, doi: DOI: https://doi.org/10.29207/resti.v8i4.5911.
F. A. Putra, S. Mirajdandi, B. Okmarizal, and S. Mulyanda, “Prediksi Dropout Mahasiswa?: Early-Warning Berbasis Enrollment dengan Machine Learning,” J. FASILKOM, vol. 15, no. 3, pp. 465–473, 2025, doi: DOI: https://doi.org/10.37859/jf.v15i3.10714.
S. Bahri and D. M. Midyanti, “Penerapan Metode K-Medoids Untuk Pengelompokan Mahasiswa Application Of K-Medoids Method For Dropout,” J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 1, pp. 165–172, 2023, doi: 10.25126/jtiik.2023106643.
M. H. Ariansyah, E. N. Fitri, and S. Winarno, “Improving Performance Of Students ’ Grade Classification Model Uses Naïve Bayes Gaussian Tuning Model And Feature Selection,” J. Tek. Inform., vol. 4, no. 3, pp. 493–501, 2023, doi: DOI: https://doi.org/10.52436/1.jutif.2023.4.3.737.
D. A. Rahmawati, N. A. Ibadurrahman, J. Zeniarja, N. Hendriyanto, I. Engineering, and I. Engineering, “Implementation Of The Random Forest Algorithm In Classifying The Accuracy Of Graduation Time For Computer Engineering,” J. Tek. Inform., vol. 4, no. 3, pp. 565–572, 2023, doi: DOI: https://doi.org/10.52436/1.jutif.2023.4.3.920.
S. Gesti, A. Utami, H. Setiadi, and A. Rohmadi, “Comparative Analysis of Machine Learning Algorithms with RFE-CV for Student Dropout Prediction,” J. Tek. Inform., vol. 6, no. 3, pp. 1319–1338, 2025, doi: DOI: https://doi.org/10.52436/1.jutif.2025.6.3.4695.
Y. Desnelita, N. Nasution, L. Suryati, and F. Zoromi, “Dampak SMOTE terhadap Kinerja Random Forest Classifier berdasarkan Data Tidak seimbang Impact of SMOTE on Random Forest Classifier Performance based on Imbalanced Data,” Matrik J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 21, no. 3, 2022, doi: 10.30812/matrik.v21i3.1726.
M. Ardianti, O. D. Nurhayati, and B. Warsito, “Model Prediksi Kinerja Siswa Berdasarkan Data Log LMS Menggunakan Ensemble Machine Learning,” J. Sains dan Teknol., vol. 12, no. 3, pp. 562–571, 2023, doi: https://doi.org/10.23887/jstundiksha.v12i3.59816.
P. Sejati et al., “Studi Komparasi Naive Bayes , K-Nearest Neighbor , Dan Random Forest Untuk Prediksi Calon Mahasiswa Yang Diterima Atau Comparative Study Of Naive Bayes , K-Nearest Neighbor , And Random Forest For The Prediction Of Prospective Students,” J. Teknol. Inf. dan Ilmu Komput., vol. 9, no. 7, pp. 1341–1348, 2022, doi: 10.25126/jtiik.202296737.
S. Sza et al., “Penerapan Decision Tree Dan Random Forest Dalam Deteksi The Application Of Decision Tree And Random Forest In Detecting Human Stress Levels Based On Sleep Conditions,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 5, pp. 1043–1050, 2024, doi: 10.25126/jtiik.2024117993.
N. F. Mahing, A. L. Gunawan, A. Foresta, and A. Zen, “Klasifikasi Tingkat Stres Dari Data Berbentuk Teks Dengan Menggunakan Algoritma Support Vector Machine ( Svm ) Dan Classification Of Stress Levels From Text Data Using Support Vector Machine ( Svm ) Algorithm And Random Forest,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 5, 2024, doi: 10.25126/jtiik2024118010.
A. N. Pratiwi et al., “Prediksi Kinerja Akademik Matematika Siswa berdasarkan Kepribadian Big Five menggunakan Random Forest dengan Teknik Synthetic Minority Over - Sampling Personality Traits using Random Forest with Synthetic Minority Over - Sampling,” Sist. J. Sist. Inf., vol. 14, no. 2, pp. 985–1000, 2025, doi: DOI: https://doi.org/10.32520/stmsi.v14i2.5102.
A. A. Yaqin, M. A. Barata, and N. Mahmudah, “Implementation of the Random Forest Algorithm with Optuna Optimization in Lung Cancer Classification,” Sist. J. Sist. Inf., vol. 14, no. 2, pp. 561–569, 2025, doi: DOI: https://doi.org/10.32520/stmsi.v14i2.4877.
M. P. Pulungan, A. Purnomo, A. Kurniasih, P. Korespondensi, I. Class, and S. M. O. Technique, “Penerapan Smote Untuk Mengatasi Imbalance Class Dalam Klasifikasi Kepribadian Mbti Menggunakan Naive Bayes Application Of Smote To Overcome Class Imbalance In The Mbti Personality Classification Using The Naïve Bayes Classifier,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 5, pp. 1033–1042, 2024, doi: 10.25126/jtiik.2024117989.
U. Bumigora and P. Korespondensi, “Peningkatan Kinerja Metode Svm Menggunakan Metode Knn Imputasi Dan K-Means-Smote Untuk Klasifikasi Kelulusan Improvement Performance Of Svm Method Using Knn Imputation And K-Means-Smote Method For Graduation Classification Of,” J. Teknol. Inf. dan Ilmu Komput., vol. 8, no. 4, pp. 713–718, 2021, doi: 10.25126/jtiik.202183428.
R. Artikel, R. A. Nurdian, M. Ridwan, and A. Yusuf, “Komparasi Metode SMOTE dan ADASYN dalam Meningkatkan Performa Klasifikasi Herregistrasi Mahasiswa Baru,” J. Tek. Inform. dan Sist. Inf., vol. 8, no. April, pp. 24–32, 2022, doi: http://dx.doi.org/10.28932/jutisi.v8i1.4004 Riwayat.
N. N. Sholihah and A. Hermawan, “Implementation Of Random Forest And Smote Methods For Economic Status Classification In Cirebon City,” J. Tek. Inform., vol. 4, no. 6, pp. 1387–1397, 2023, doi: DOI: https://doi.org/10.52436/1.jutif.2023.4.6.1135.
T. Gori et al., “Preprocessing Data Dan Klasifikasi Untuk Prediksi Kinerja Data Preprocessing And Classification For Predicting Student,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 1, pp. 215–224, 2024, doi: 10.25126/jtiik.20241118074.
D. S. Bhakti, A. Prasetyo, P. Arsi, C. S. Faculty, and U. A. Purwokerto, “Implementation Of Hyperparameter Tuning In Random Forest Implementasi Hyperparameter Tuning Pada Algoritma Random,” J. Tek. Inform., vol. 5, no. 4, pp. 63–69, 2024, doi: DOI: https://doi.org/10.52436/1.jutif.2024.5.4.2032.
F. Nuraeni, D. Kurniadi, M. H. Diazki, K. Garut, P. Korespondensi, and K. Karyawan, “Algoritma K-Nearest Neighbor Pada Kasus Dataset Imbalanced K-Nearest Neighbor Algorithm And Smote Method,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 3, pp. 557–568, 2024, doi: 10.25126/jtiik.938144.
A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 2nd ed. Sebastopol, CA: O’Reilly Media, Inc., 2022.
G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning, 2nd ed. New York, NY: Springer, 2021.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Optimasi Kinerja Algoritma Random Forest dengan SMOTE untuk Prediksi Kinerja Akademik Siswa
ARTICLE HISTORY
Issue
Section
Copyright (c) 2026 Muhammad Rizky Ramadhan, Solikhun Solikhun
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
