Analisis Komparatif Determinan Prestasi Matematika dan Bahasa Indonesia Menggunakan Random Forest dan SHAP
DOI:
https://doi.org/10.35968/jsi.v13i2.2111Keywords:
Educational Data Mining, Student Performance Prediction, Feature Importance, SHAP, Random ForestAbstract
This study aims to compare the determinants of academic performance between Mathematics and Indonesian Language subjects using an Educational Data Mining approach. Utilizing the UCI Student Performance dataset, comprising 395 Mathematics and 649 Indonesian Language students, we identified 382 students who were enrolled in both subjects through identity-based merging. Random Forest models were optimized via Grid Search and evaluated using RMSE, MAE, and R², while SHAP (SHapley Additive exPlanations) was employed for model interpretability. The results indicate that the Random Forest model achieved higher predictive accuracy for Indonesian Language (R² = 0.85) compared to Mathematics (R² = 0.78). Feature importance and SHAP analyses revealed significant differential impacts: Mathematics performance was predominantly influenced by absences (r = -0.28), study time (r = 0.31), and weekend alcohol consumption (r = -0.22), whereas Indonesian Language performance was more strongly determined by maternal (r = 0.32) and paternal (r = 0.28) education levels. We conclude that educational intervention strategies should be tailored specifically to each subject rather than applying a generalized approach.References
Adawiya, R., & Csíkos, C. (2026). Exploring the interactions between metacognitive strategies, emotional factors, and mathematics performance: Evidence from a CB-SEM model in Indonesian high school students. Acta Psychologica, 262. https://doi.org/10.1016/J.ACTPSY.2025.106131
Awaludin, M., Nuryadi, H., & Pribadi, G. N. (2024). Sistem Otomatisasi Laporan untuk Optimalisasi Pelaporan Data Penelitian dan Pengabdian kepada Masyarakat di Universitas Dirgantara Marsekal Suryadarma. 9675, 1–7.
Banjarnahor, E., Wibawanta, B., Belferik, R., Sadeva, T. A. P., & Andriani, N. (2025). Implementation of Machine Learning Models to Predict First-Year Student Achievement Based on Ethnicity and Entrance Test Scores. 2025 1st International Conference on Data Science and Geoinformatics (ICDSG), 370–375. https://doi.org/10.1109/ICDSG67714.2025.11381374
Cortez, P., & Silva, A. (2008). Using data mining to predict secondary school student performance. 15th European Concurrent Engineering Conference 2008, ECEC 2008 - 5th Future Business Technology Conference, FUBUTEC 2008, 2003(2000), 5–12.
Henry Wasosa. (2025). Influence of Psychological Well-Being and School Factors on Delinquency. International Journal of Research and Innovation in Social Science (IJRISS), VII(2454), 1175–1189. https://doi.org/10.47772/IJRISS
Lailawati, Najmuddin, & Siraj. (2025). Implementation of the Independent Learning Curriculum in Improving Student Learning Outcomes. Jurnal Inovasi Pendidikan Dan Sains, 6(3), 580–586.
MZ, M., Mailizar, M., & Elizar, E. (2025). Understanding Indonesian Students’ Mathematics Performance: A Secondary Analysis of PISA Data. Jurnal Didaktik Matematika, 12(1), 181–195. https://doi.org/10.24815/JDM.V12I1.44700
Rifka Alkhilyatul Ma’rifat, I Made Suraharta, I. I. J. (2024). Independent Curriculum in Improving the Quality of Education Putri. Education Achievment: Journal of Science and Research, 2(2), 306–312.
Satria, D., Permani, R., Winarno, K., Kaluge, D., Indraswari, C. R., & Handrito, R. P. (2025). an Exploratory Study of High-Educated Poverty Through Machine Learning Approach: a Case Study of East Java, Indonesia. Business, Management and Economics Engineering, 23(1), 92–107. https://doi.org/10.3846/bmee.2025.20808
Siti Marhamah Winarti, Nur Ahyani, & Nurlina Nurlina. (2025). The Influence of Independent Curriculum and Classroom Management on Elementary Students’ Learning Outcomes in Ogan Ilir. International Journal of Educational Development, 2(3), 09–18. https://doi.org/10.61132/ijed.v2i3.307
Tiopan Octavianus Sitorus, P. A., Indrianti, Y., Sasmoko, Manalu, S. R., & Anindyo Widhoyoko, S. (2025). Identifying Key Drivers of the Indonesian Entrepreneurial Performance Using Machine Learning and RapidMiner. International Conference on Information Management and Technology, 686–691. https://doi.org/10.1109/ICIMTECH67074.2025.11265240
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 JSI (Jurnal Sistem Informasi) Universitas Suryadarma

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
