Evaluasi Ensemble Learning untuk Prediksi Nilai Matematika Siswa Sekolah Menengah
DOI:
https://doi.org/10.52436/1.jpti.858Kata Kunci:
ensemble learning, prediksi nilai siswa, Random Forest, MLP, Gradient Boosting, stacking, pendidikanAbstrak
Prediksi dini performa matematika siswa sekolah menengah sangat penting untuk merancang intervensi pendidikan yang lebih adaptif dan efektif sebelum ujian akhir resmi dilaksanakan. Penelitian ini bertujuan untuk mengevaluasi kinerja tiga model machine learning Random Forest (RF), Gradient Boosting Regressor (GBR), dan Multi-Layer Perceptron (MLP) dalam memprediksi nilai matematika siswa di Indonesia, serta mendokumentasikan proses tuning hyperparameter secara sistematis untuk setiap model. Dataset yang digunakan terdiri dari skor matematika, membaca, menulis, serta variabel demografis meliputi jenis kelamin, latar belakang pendidikan orang tua, jenis layanan makan, dan keikutsertaan kursus persiapan. Proses tuning hyperparameter untuk RF dan GBR dilakukan menggunakan RandomizedSearchCV dengan 5-fold cross-validation, menguji rentang nilai untuk jumlah estimator, kedalaman maksimum pohon, dan laju pembelajaran (learning rate). Sedangkan pada Multi-Layer Perceptron, GridSearchCV diterapkan dengan variasi arsitektur hidden_layer_sizes, laju pembelajaran awal (learning_rate_init), dan faktor regularisasi (alpha) pada 5-fold CV. Model diukur menggunakan Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan koefisien determinasi (R²). Hasil eksperimen menunjukkan bahwa GBR memberikan performa terbaik dengan MAE sebesar 11,61 poin, RMSE 15,23 poin, dan R² 0,10. Random Forest menempati urutan kedua (MAE 12,34; RMSE 16,05; R² 0,64), diikuti MLP (MAE 13,10; RMSE 17,20; R² 0,60). Analisis feature importance mengungkap bahwa skor membaca dan menulis bersama-sama menyumbang lebih dari 60 % kontribusi prediksi, sedangkan faktor demografis seperti latar belakang pendidikan orang tua dan keikutsertaan kursus berperan sekunder namun tetap signifikan. Temuan ini mengindikasikan bahwa model ensemble learning tidak hanya unggul dalam akurasi prediksi, tetapi juga memberikan wawasan mendalam tentang variabel kunci yang memengaruhi performa matematika siswa. Implementasi model ini memungkinkan guru dan pihak sekolah untuk mengidentifikasi siswa yang berisiko rendah secara lebih cepat, merancang program remedial atau pengayaan yang tepat sasaran, serta memanfaatkan sumber daya pendidikan secara lebih efisien. Untuk penelitian lanjutan, disarankan penambahan variabel perilaku siswa seperti durasi belajar mandiri dan kehadiran serta eksplorasi model sekuensial (RNN/Transformer) untuk menangkap dinamika pembelajaran dari waktu ke waktu.
Unduhan
Referensi
R. Syafitri, Z. H. Putra, and E. Noviana, “Fifth Grade Students’ Logical Thinking in Mathematics,” Journal of Teaching and Learning in Elementary Education, vol. 3, no. 2, p. 157, 2020, doi:10.33578/jtlee.v3i2.7840.
L. Gan and T. T. Wijaya, “Measuring Student’s Logical Reasoning Skills of Chinese Senior High School Using Rasch Measurement Model,” Jurnal Mathedu (Mathematic Education Journal), vol. 4, no. 3, pp. 142–149, 2021, doi:10.37081/mathedu.v4i3.3247.
W. F. W. Yaacob, S. A. M. Nasir, W. F. W. Yaacob, and N. M. Sobri, “Supervised Data Mining Approach for Predicting Student Performance,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 16, no. 3, pp. 1584–1592, 2019, doi:10.11591/ijeecs.v16.i3.pp1584-1592.
A. Oyedeji, A. M. Salami, O. Folorunsho, and O. Abolade, “Analysis and Prediction of Student Academic Performance Using Machine Learning,” Journal of Information Technology and Computer Engineering (JITCE), vol. 4, no. 1, pp. 10–15, 2020, doi:10.25077/jitce.4.01.10-15.2020.
L. K. Weir, M. K. Barker, L. McDonnell, N. G. Schimpf, T. M. Rodela, and P. M. Schulte, “Small Changes, Big Gains: A Curriculum-Wide Study of Teaching Practices and Student Learning in Undergraduate Biology,” PLOS ONE, vol. 14, no. 8, p. e0220900, 2019, doi:10.1371/journal.pone.0220900.
S. Moon, M. A. Jackson, J. H. Doherty, and M. P. Wenderoth, “Evidence-Based Teaching Practices Correlate With Increased Exam Performance in Biology,” PLOS ONE, vol. 16, no. 11, p. e0260789, 2021, doi:10.1371/journal.pone.0260789.
S. F. Reardon, “The Widening Academic Achievement Gap Between the Rich and the Poor,” in Inequality in Education, London, UK: Routledge, 2018, pp. 177–189, doi:10.4324/9780429499821-33.
I. Altschul, “Linking Socioeconomic Status to the Academic Achievement of Mexican American Youth Through Parent Involvement in Education,” Journal of the Society for Social Work and Research, vol. 3, no. 1, pp. 13–30, 2012, doi:10.5243/jsswr.2012.2.
H. Hafrizal, U. Kasim, and I. A. Samad, “Students’ Perception Toward English Subject and Their Learning Outcome,” English Education Journal, vol. 12, no. 3, pp. 476–494, 2021, doi:10.24815/eej.v12i3.19251.
W. H. Jeynes, “A Meta-Analysis of the Efficacy of Different Types of Parental Involvement Programs for Urban Students,” Urban Education, vol. 47, no. 4, pp. 706–742, 2012, doi:10.1177/0042085912445643.
H. E. Kagosi, T. Mandila, and G. Koda, “Parental Contribution to Their Children’s Education in Public Secondary Schools in Lushoto District Council, Tanzania,” International Journal of Innovative Research and Development, vol. 10, no. 10, 2021, doi:10.24940/ijird/2021/v10/i10/oct21005.
L. L. Pinatil, C. G. G. Trinidad, G. C. Englis, J. R. Miñoza, I. C. M. Corriente, and G. A. Trinidad, “Parental Involvement and Academic Performance of Education Students in a State University in the Philippines,” International Journal of Science and Management Studies (IJSMS), vol. 5, no. 3, pp. 95–99, 2022, doi:10.51386/25815946/ijsms-v5i3p110.
S. Ghimire, P. Guéguen, A. Pothon, and D. Schorlemmer, “Testing Machine Learning Models for Heuristic Building Damage Assessment Applied to the Italian Database of Observed Damage (DaDO),” Natural Hazards and Earth System Sciences, vol. 23, no. 10, pp. 3199–3218, 2023, doi:10.5194/nhess-23-3199-2023.
L. Sari, A. Romadloni, R. Lityaningrum, and H. D. Hastuti, “Implementation of LightGBM and Random Forest in Potential Customer Classification,” TIERS Information Technology Journal, vol. 4, no. 1, pp. 43–55, 2023, doi:10.38043/tiers.v4i1.4355.
A. A. J. Ghanim et al., “An Improved Flood Susceptibility Assessment in Jeddah, Saudi Arabia, Using Advanced Machine Learning Techniques,” Water, vol. 15, no. 14, p. 2511, 2023, doi:10.3390/w15142511.
G. Biau, B. Cadre, and L. Rouvìère, “Accelerated Gradient Boosting,” Machine Learning, vol. 108, no. 6, pp. 971–992, 2019, doi:10.1007/s10994-019-05787-1.
S. Zhang, J. Chen, W. Zhang, Q. Xu, and J. Shi, “Education Data Mining Application for Predicting Students’ Achievements of Portuguese Using Ensemble Model,” Science Journal of Education, vol. 9, no. 2, p. 58, 2021, doi:10.11648/j.sjedu.20210902.16.
V. Liulka, O. Savenkova, and A. Dedukhno, “The Peculiarities of Using Artificial Intelligence in Teaching Foreign Languages in Higher Education Institutions in Ukraine,” Humanities Science Current Issues, vol. 2, no. 73, pp. 195–201, 2024, doi:10.24919/2308-4863/73-2-30.
C. Xing, “Research on the Application of Artificial Intelligence Empowered Education Management,” Journal of Artificial Intelligence Practice, vol. 6, no. 6, 2023, doi:10.23977/jaip.2023.060602.
A. Çay?r, “A Literature Review on the Effect of Artificial Intelligence on Education,” ?nsan ve Sosyal Bilimler Dergisi, vol. 6, no. 2, pp. 276–288, 2023, doi:10.53048/johass.1375684.
D. Yang, E.-S. Oh, and Y. Wang, “Hybrid Physical Education Teaching and Curriculum Design Based on a Voice Interactive Artificial Intelligence Educational Robot,” Sustainability, vol. 12, no. 19, p. 8000, 2020, doi:10.3390/su12198000.
V. B. S., K. L. Buchupalli, R. R. Gottimukkula, and S. Kalimuthu, “Enhanced Diagnostic Accuracy in Musculoskeletal Radiography: A Comprehensive Ensemble Approach of Deep Learning Models,” Preprint, 2024, doi:10.21203/rs.3.rs-3963697/v1.
S. Ye, H. Xiao, and L. Zhou, “Small Accommodation Business Growth in Rural Areas: Effects on Guest Experience and Financial Performance,” International Journal of Hospitality Management, vol. 76, pp. 29–38, Jan. 2019, doi:10.1016/j.ijhm.2018.03.016.
J. Liu, H. Sun, Y. Li, W. Fang, and S. Niu, “An Improved Power System Transient Stability Prediction Model Based on mRMR Feature Selection and WTA Ensemble Learning,” Applied Sciences, vol. 10, no. 7, p. 2255, 2020, doi:10.3390/app10072255.
T. Turino, R. E. Saputro, and G. Karyono, “Penerapan Model Ensemble Learning dengan Random Forest dan Multi-Layer Perceptron untuk Prediksi Gempa,” Jurnal Pendidikan dan Teknologi Indonesia, vol. 5, no. 2, Feb. 2025, doi:10.52436/1.jpti.667.
X. Wang et al., “Small Earthquakes Can Help Predict Large Earthquakes: A Machine Learning Perspective,” Applied Sciences, vol. 13, no. 11, p. 6424, 2023, doi:10.3390/app13116424.
N. Agarwal, I. Arora, H. Saini, and U. Sharma, “A Novel Approach for Earthquake Prediction Using Random Forest and Neural Networks,” EAI Endorsed Transactions on Energy Web, vol. 10, 2023, doi:10.4108/ew.4329.
A. Malekloo, E. Özer, M. AlHamaydeh, and M. Girolami, “Machine Learning and Structural Health Monitoring Overview With Emerging Technology and High-Dimensional Data Source Highlights,” Structural Health Monitoring, vol. 21, no. 4, pp. 1906–1955, 2021, doi:10.1177/14759217211036880.
“Students Performance in Exams,” Kaggle, https://www.kaggle.com/datasets/spscientist/students-performance-in-exams (accessed Jul. 30, 2025).
S. Ye, H. Zhang, F. Shi, J. Guo, S. Wang, and B. Zhang, “Ensemble Learning to Improve the Prediction of Fetal Macrosomia and Large-for-Gestational Age,” Journal of Clinical Medicine, vol. 9, no. 2, p. 380, 2020, doi:10.3390/jcm9020380.
D. Wahyudin et al., Kajian Akademik Kurikulum Merdeka, Pusat Kurikulum dan Pembelajaran, Badan Standar, Kurikulum, dan Asesmen Pendidikan, Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi, 2024.
