Clustering Pola Tidur dan Kebiasaan Belajar Siswa untuk Segmentasi Strategi Belajar dan Prediksi Performa Ujian

Dedy Wahyudi; Moh.  Zainuddin; Sunu  Jatmika

doi:10.69693/dcs.v3i2.101

Authors

Dedy Wahyudi Institut Teknologi dan Bisnis Asia Malang
Moh. Zainuddin Institut Teknologi dan Bisnis Asia Malang
Sunu Jatmika Institut Teknologi dan Bisnis Asia Malang

DOI:

https://doi.org/10.69693/dcs.v3i2.101

Keywords:

Data Mining Pendidikan, K-Means, Prediksi Performa, Pola Tidur, Kebiasaan Belajar

Abstract

Penelitian ini bertujuan mengidentifikasi segmentasi pola tidur dan kebiasaan belajar serta menguji kontribusinya terhadap prediksi performa ujian. Dataset terdiri atas 1.000 observasi dengan 10 atribut, tanpa nilai hilang dan duplikasi. Clustering K-Means diterapkan pada tujuh fitur perilaku dengan k=2–6 yang dievaluasi menggunakan silhouette, Calinski–Harabasz, dan Davies–Bouldin. Prediksi nilai dibandingkan antara mean baseline, regresi linear, Ridge, random forest, dan gradient boosting dengan validasi silang 10-fold. Solusi k=5 memperoleh silhouette tertinggi sebesar 0,125 dan Davies–Bouldin 1,869, menghasilkan lima profil: belajar rendah–tidur pendek; belajar intensif–stres dan media tinggi; tidur cukup–stres tinggi; tidur panjang–media sosial tinggi; dan belajar intensif–gaya hidup terkendali. Nilai antarkelompok berbeda signifikan (ANOVA F=66,459; p<0,001; η²=0,211), tetapi silhouette rendah menunjukkan tumpang tindih yang kuat. Ridge memberikan prediksi terbaik (MAE=3,845; RMSE=4,442; R²=0,567), sedangkan penambahan cluster secara fold-local tidak meningkatkan prediksi (RMSE=4,452; R²=0,565). Dengan demikian, clustering relevan untuk menyusun strategi belajar tersegmentasi, tetapi label cluster tidak menambah informasi prediktif di luar fitur asli. Hasil ditafsirkan secara eksploratif karena provenance dataset tidak tersedia.

Downloads

Download data is not yet available.

References

Alawi, S. J. S., Shaharanee, I. N. M., & Jamil, J. M. (2023). Clustering student performance data using K-means algorithms. Journal of Computational Innovation and Analytics, 2(1), 41–55. https://doi.org/10.32890/jcia2023.2.1.3

Albreiki, B., Zaki, N., & Alashwal, H. (2021). A systematic literature review of student performance prediction using machine learning techniques. Education Sciences, 11(9), 552. https://doi.org/10.3390/educsci11090552

Bickerdike, A., O’Deasmhunaigh, C., O’Flynn, S., & O’Tuathaigh, C. (2016). Learning strategies, study habits and social networking activity of undergraduate medical students. Advances in Health Sciences Education, 21, 1021–1031. https://doi.org/10.1007/s10459-016-9689-0

Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324

Hoerl, A. E., & Kennard, R. W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1), 55–67. https://doi.org/10.1080/00401706.1970.10488634

MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the Fifth Berkeley Symposium (pp. 281–297).

Mohd Talib, N. I., et al. (2023). Identification of student behavioral patterns in higher education using clustering and classification. Applied Sciences, 13(5), 3267. https://doi.org/10.3390/app13053267

Musshafen, L. A., et al. (2021). Associations between sleep and academic performance in US adolescents: A systematic review and meta-analysis. Sleep Medicine, 83, 71–82. https://doi.org/10.1016/j.sleep.2021.04.015

Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830. https://jmlr.org/papers/v12/pedregosa11a.html

Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65. https://doi.org/10.1016/0377-0427(87)90125-7

Walck-Shannon, E. M., Rowell, S. F., & Frey, R. F. (2021). To what extent do study habits relate to performance? CBE—Life Sciences Education, 20(1). https://doi.org/10.1187/cbe.20-05-0091

Wang, M., et al. (2025). Sleep duration and subject-specific academic performance among adolescents. npj Science of Learning. https://www.nature.com/articles/s41539-025-00361-y

Wu, M. (2026). K-Means clustering-based feature generation for student performance prediction. Transactions on Educational Data Mining. https://www.icck.org/article/abs/tedm.2026.716076

Zeek, M. L., et al. (2015). Sleep duration and academic performance among student pharmacists. American Journal of Pharmaceutical Education, 79(5), 63. https://doi.org/10.5688/ajpe79563

Zhang, Y., et al. (2021). Educational data mining techniques for student performance prediction. Frontiers/PMC. https://pmc.ncbi.nlm.nih.gov/articles/PMC8688359/