Perbandingan Algoritma Random Forest, Decision Tree, dan K-Nearest Neighbor untuk Penentuan Model Klasifikasi Gaya Belajar VARK
DOI:
https://doi.org/10.25181/rt.v4i2.5086Kata Kunci:
VARK Learning Style, Machine Learning, Random Forest, Educational Data Mining, Adaptive LearningAbstrak
Ketidaksesuaian antara metode pengajaran dengan preferensi gaya belajar individu dalam platform e-learning sering kali menyebabkan rendahnya efektivitas penyerapan informasi bagi mahasiswa. Masalah utama terletak pada pendekatan pembelajaran one size fits all serta inefisiensi metode identifikasi gaya belajar melalui kuesioner manual yang bersifat subjektif dan memakan waktu. Penelitian ini bertujuan untuk melakukan analisis komparatif terhadap tiga algoritma Machine Learning yaitu Random Forest, Decision Tree, dan K-Nearest Neighbor (KNN) guna menentukan model klasifikasi yang paling presisi dan stabil untuk memetakan gaya belajar VARK (Visual, Auditory, Read/Write, Kinesthetic) mahasiswa. Metodologi penelitian mengikuti kerangka kerja CRISP-DM menggunakan dataset sebanyak 1.410 record yang telah diseimbangkan melalui penambahan sampel sintetis. Hasil eksperimen menunjukkan bahwa Random Forest dan KNN memperoleh nilai akurasi tertinggi yang identik, yaitu sebesar 97,87%, sementara Decision Tree mencatatkan akurasi 95,39%. Namun, berdasarkan evaluasi stabilitas melalui K-Fold Cross Validation, Random Forest terbukti sebagai model paling optimal dengan nilai Mean CV tertinggi sebesar 0,9592 dibandingkan KNN 0,9503. Temuan ini memberikan fondasi ilmiah yang kuat bagi pengembangan sistem rekomendasi adaptif seperti aplikasi Flex Learning untuk menyajikan materi ajar yang benar-benar personal dan efektif bagi mahasiswa.
Unduhan
Referensi
[1] E. du Plooy, D. Casteleijn, and D. Franzsen, “Personalized adaptive learning in higher education: A scoping review of key characteristics and impact on academic performance and engagement,” Nov. 15, 2024, Elsevier Ltd. doi: 10.1016/j.heliyon.2024.e39630.
[2] F. Abomelha and P. Newbury, “A VARK learning style-based Recommendation system for Adaptive E-learning,” in Communication Papers of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS), PTI, Nov. 2024, pp. 1–8. doi: 10.15439/2024f5253.
[3] S. L. Lew, C. W. Tang, and S. Y. Ooi, “Improving Online Learning via VARK Learning Styles and Machine Learning-Driven Personalisation.”
[4] O. El Aissaoui, Y. El Madani El Alami, L. Oughdir, and Y. El Allioui, “A hybrid machine learning approach to predict learning styles in adaptive e-learning system,” in Advances in Intelligent Systems and Computing, Springer Verlag, 2019, pp. 772–786. doi: 10.1007/978-3-030-11928-7_70.
[5] E. Kalita et al., “Educational data mining: a 10-year review,” Dec. 01, 2025, Springer Science and Business Media B.V. doi: 10.1007/s10791-025-09589-z.
[6] I. Z. Fawwas et al., “Learning Method Recommendation Based on VARK Model Using Certainty Factor Algorithm,” in BIO Web of Conferences, EDP Sciences, Nov. 2023. doi: 10.1051/bioconf/20237501007.
[7] E. El-Saftawy, A. A. A. Latif, A. M. ShamsEldeen, M. A. Alghamdi, A. M. Mahfoz, and B. E. Aboulhoda, “Influence of applying VARK learning styles on enhancing teaching skills: application of learning theories,” BMC Med. Educ., vol. 24, no. 1, Dec. 2024, doi: 10.1186/s12909-024-05979-x.
[8] Z. I. Bimawan, T. Astuti, and P. Arsi, “Comparison Of Random Forest, K-Nearest Neighbor, Decision Tree, And XGBoost Algorithms For Detecting Stunting In Toddlers,” Jurnal Teknik Informatika (Jutif), vol. 5, no. 6, pp. 1599–1607, Sep. 2024, doi: 10.52436/1.jutif.2024.5.6.2629.
[9] A. R. Sayed, M. H. Khafagy, M. Ali, and M. H. Mohamed, “Exploring the VAK model to predict student learning styles based on learning activity,” Intelligent Systems with Applications, vol. 25, Mar. 2025, doi: 10.1016/j.iswa.2025.200483.
[10] T. Wongvorachan, S. He, and O. Bulut, “A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining,” Information (Switzerland), vol. 14, no. 1, Jan. 2023, doi: 10.3390/info14010054.
[11] F. M. Alnassar, T. Blackwell, E. Homayounvala, and M. Yee-king, “Addressing Class Imbalance in Predicting Student Performance Using SMOTE and GAN Techniques,” Applied Sciences (Switzerland), vol. 16, no. 7, Apr. 2026, doi: 10.3390/app16073274.
[12] N. Mduma, “Data Balancing Techniques for Predicting Student Dropout Using Machine Learning,” Data (Basel)., vol. 8, no. 3, Mar. 2023, doi: 10.3390/data8030049.
[13] C. Romero and S. Ventura, “Educational Data mining and Learning Analytics: An updated survey.”
[14] D. Khairy, N. Alharbi, M. A. Amasha, M. F. Areed, S. Alkhalaf, and R. A. Abougalala, “Prediction of student exam performance using data mining classification algorithms,” Educ. Inf. Technol. (Dordr)., vol. 29, no. 16, pp. 21621–21645, Nov. 2024, doi: 10.1007/s10639-024-12619-w.
[15] M. Yağcı, “Educational data mining: prediction of students’ academic performance using machine learning algorithms,” Smart Learning Environments, vol. 9, no. 1, Dec. 2022, doi: 10.1186/s40561-022-00192-z.
[16] J. Homepage, A. Aman, N. P. Rahrahima, and A. Fitri, “IJATIS: Indonesian Journal of Applied Technology and Innovation Science Implementation of Machine Learning Algorithms for Predicting Student Academic Performance,” vol. 3, no. 1, pp. 1–9, 2026, doi: 10.57152/IJATIS.v3i1.1871.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Hefri Juanto, M Said Hasibuan , Sriyanto
Artikel ini berlisensi Creative Commons Attribution 4.0 International License.
