Penerapan Algoritma XGBoost untuk Prediksi Tingkat Pemahaman Siswa pada Praktikum Laboratorium Komputer
DOI:
https://doi.org/10.62712/juktisi.v5i2.1582Keywords:
Xgboost, Pembelajaran Mesin, Prediksi, Tingkat Pemahaman Siswa, Praktikum Laboratorium KomputerAbstract
Evaluasi tingkat pemahaman siswa pada praktikum laboratorium komputer masih sering dilakukan secara manual berdasarkan nilai dan observasi guru, sehingga membutuhkan waktu dan berpotensi menimbulkan subjektivitas. Penelitian ini bertujuan menerapkan algoritma Extreme Gradient Boosting (XGBoost) sebagai solusi untuk memprediksi tingkat pemahaman siswa secara objektif, cepat, dan berbasis data. Penelitian menggunakan pendekatan kuantitatif dengan 120 data siswa yang terbagi seimbang ke dalam kategori rendah, sedang, dan tinggi. Variabel prediktor meliputi nilai kuis, nilai praktikum, kehadiran, waktu pengerjaan, keaktifan, dan observasi guru. Tahapan penelitian mencakup pengumpulan dan prapemrosesan data, pengodean label, serta pembagian data secara terstratifikasi dengan komposisi 80% data latih dan 20% data uji. Model kemudian dilatih menggunakan XGBoost dan dievaluasi melalui matriks konfusi, akurasi, presisi, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model berhasil mengklasifikasikan 23 dari 24 data uji dengan benar, dengan akurasi sebesar 95,83%, presisi 95,62%, recall 95,83%, dan F1-score 95,69%. Analisis kepentingan fitur menunjukkan bahwa nilai kuis merupakan variabel paling berpengaruh. Dengan demikian, XGBoost efektif digunakan sebagai pendukung evaluasi pembelajaran untuk membantu guru mengidentifikasi tingkat pemahaman siswa secara lebih akurat dan efisien.
Downloads
References
[1] M. O. Capao, V. S. Rosales, J. V. H. Leuterio, Q. Faith, and R. B. Requino, “Mobile Simulation-Based Learning ( MSBL ): An Integrated Basic Electronics,” J. Tech. Educ. Train., vol. 17, no. 3, pp. 64–78, 2025, doi: https://doi.org/10.30880/jtet.2025.17.03.005.
[2] Ç. Atmaca, “Online teaching practicum procedures during the COVID-19 pandemic in Turkish EFL context,” vol. 20, no. 4, pp. 352–369, 2023, doi: https://doi.org/10.1177/20427530231156677.
[3] H. Subandiyah, R. Nasrullah, R. Ramadhan, H. Supratno, R. P. Raharjo, and F. Lukman, “The impact of differentiated instruction on student engagement and achievement in Indonesian language learning,” Cogent Educ., vol. 12, no. 1, p., 2025, doi: https://doi.org/10.1080/2331186X.2025.2516378.
[4] A. Aydınlar et al., “Awareness and level of digital literacy among students receiving health-based education,” BMC Med. Educ., vol. 24, no. 38, pp. 1–13, 2024, doi: 10.1186/s12909-024-05025-w.
[5] C. Lu and M. Cutumisu, “Online engagement and performance on formative assessments mediate the relationship between attendance and course performance,” Int. J. Educ. Technol. High. Educ., vol. 19, no. 2, 2022, doi: https://doi.org/10.1186/s41239-021-00307-5.
[6] W. Liu, Z. Chen, and Y. Hu, “XGBoost algorithm-based prediction of safety assessment for pipelines,” Int. J. Press. Vessel. Pip., vol. 197, p. 104655, 2022, doi: https://doi.org/10.1016/j.ijpvp.2022.104655.
[7] H. Liu, X. Chen, and X. Liu, “Factors influencing secondary school students ’ reading literacy : An analysis based on XGBoost and SHAP methods,” Front. Psychol., vol. 13, no. 948612, 2022, doi: 10.3389/fpsyg.2022.948612.
[8] M. Yang, Z. Li, and S. Liu, “A Machine Learning Based Framework for Predictive School Management Using Student and Faculty Analytics,” Sci. Rep., vol. 16, no. 16224, pp. 1–31, 2026, doi: https://doi.org/10.1038/s41598-026-47278-z.
[9] B. Cheng, Y. Liu, and Y. Jia, “Evaluation of students ’ performance during the academic period using the XG-Boost Classifier-Enhanced AEO hybrid model,” Expert Syst. Appl., vol. 238, no. PD, p. 122136, 2024, doi: https://doi.org/10.1016/j.eswa.2023.122136.
[10] H. Guo, “An Interpretable Cross-Regional Prediction Study of University Students ’ Mental Health Based on XGBoost and SHAP,” IEEE Access, vol. 14, pp. 48025–48039, 2026, doi: https://doi.org/10.1109/ACCESS.2026.3676575.
[11] R. Natras and B. Soja, “Ensemble Machine Learning of Random Forest , AdaBoost and XGBoost for Vertical Total Electron Content Forecasting,” Remote Sens., vol. 14, pp. 1–34, 2022, doi: https://doi.org/10.3390/rs14153547.
[12] S. Hakkal and A. A. Lahcen, “Computers and Education : Artificial Intelligence XGBoost To Enhance Learner Performance Prediction,” Comput. Educ. Artif. Intell., vol. 7, p. 100254, 2024, doi: https://doi.org/10.1016/j.caeai.2024.100254.
[13] A. Villar, C. Robledo, and V. De Andrade, “Supervised machine learning algorithms for predicting student dropout and academic success : a comparative study,” Discov. Artif. Intell., vol. 4, no. 2, 2024, doi: https://doi.org/10.1007/s44163-023-00079-z.
[14] L. R. Pelima, Y. Sukmana, and Y. Rosmansyah, “Predicting University Student Graduation Using Academic Performance and Machine Learning : A Systematic Literature Review,” IEEE Access, vol. 12, no. January, pp. 23451–23465, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3361479.
[15] M. Chaudhry et al., “A Systematic Literature Review on Identifying Patterns Using Unsupervised Clustering Algorithms : A Data Mining Perspective,” Symmetry (Basel)., vol. 15, no. 1679, pp. 1–44, 2023, doi: https://doi.org/10.3390/sym15091679.
[16] M. Bilal, G. Ali, M. W. Iqbal, M. Anwar, M. Sheraz, and A. Malik, “Auto-Prep : Efficient and Automated Data Preprocessing Pipeline,” IEEE Access, vol. 10, no. August, pp. 107764–107784, 2022, doi: https://doi.org/10.1109/ACCESS.2022.3198662.
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Kecitaan Harefa, Rinna Rachmatika
This work is licensed under a Creative Commons Attribution 4.0 International License.
