PENGELOMPOKAN PROFIL KEMAMPUAN SISWA SMK BERDASARKAN HASIL TKA 2025
DOI:
https://doi.org/10.51878/vocational.v6i4.16132Keywords:
Analisis Klaster, K-Means, Profil Kemampuan Siswa, Tes Kemampuan Akademik, Pendidikan VokasiAbstract
Academic Competency Test (TKA) results encompass multiple dimensions of student ability that need to be analyzed simultaneously to provide a more comprehensive picture of academic achievement. Reliance solely on a single aggregate mean score may obscure differences in students’ strengths and weaknesses across competency domains. This study aimed to classify the ability profiles of vocational high school students based on the 2025 Academic Competency Test (TKA) results. The study employed an exploratory quantitative approach using the official collective test results of SMKN Palang. All 98 test participants were included through total sampling. The clustering variables were Indonesian, Mathematics, English, and Creative Projects and Entrepreneurship scores. The data were standardized into z-scores and analyzed using the K-Means algorithm. The number of clusters was determined by comparing the silhouette coefficient, inertia, Davies-Bouldin Index, and cluster-size balance for k = 2 to k = 6. The results indicated that a three-cluster solution was the most appropriate, with the highest silhouette coefficient of 0.296. The first cluster included 46 students (46.94%) with relatively strong and balanced achievement. The second cluster included 35 students (35.71%) who required general academic and entrepreneurship subject support. The third cluster included 17 students (17.35%) with a marked gap in English achievement. Two principal components explained 68.79% of the total variance and produced a visual pattern consistent with the K-Means solution. The findings show that student competency profiles were not homogeneous. Schools should provide targeted enrichment, integrated literacy-numeracy support, and contextual English assistance. The clusters are exploratory profiles and should not be treated as permanent student labels.
Downloads
References
Badan Standar, Kurikulum, dan Asesmen Pendidikan. (2025). Peraturan Kepala Badan Standar, Kurikulum, dan Asesmen Pendidikan Nomor 45 Tahun 2025 tentang kerangka asesmen Tes Kemampuan Akademik SMA/MA dan SMK/MAK.
Gonzalez-Nucamendi, A., Noguez, J., Neri, L., Robledo-Rella, V., García-Castelán, R. M. G., & Escobar-Castillejos, D. (2022). Learning analytics to determine profile dimensions of students associated with their academic performance. Applied Sciences, 12(20), 10560. https://doi.org/10.3390/app122010560
Handayati, P., Wulandari, D., Soetjipto, B. E., Wibowo, A., & Narmaditya, B. S. (2020). Does entrepreneurship education promote vocational students’ entrepreneurial mindset? Heliyon, 6(11), e05426. https://doi.org/10.1016/j.heliyon.2020.e05426
Kementerian Pendidikan Dasar dan Menengah Republik Indonesia. (2025a). Peraturan Menteri Pendidikan Dasar dan Menengah Nomor 9 Tahun 2025 tentang Tes Kemampuan Akademik.
Kementerian Pendidikan Dasar dan Menengah Republik Indonesia. (2025b). Keputusan Menteri Pendidikan Dasar dan Menengah Nomor 95/M/2025 tentang pedoman penyelenggaraan Tes Kemampuan Akademik.
Nafiati, D. A., Sukirno, S., Saidah, A., & Rajli, F. F. A. (2025). Vocational school entrepreneurship competence: Do intellectual skill, school grade, and learning environment matter? Jurnal Ekonomi Pendidikan dan Kewirausahaan, 13(1), 107–130. https://doi.org/10.26740/jepk.v13n1.p107-130
Orsoni, M., Giovagnoli, S., Garofalo, S., Magri, S., Benvenuti, M., Mazzoni, E., & Benassi, M. (2023). Preliminary evidence on machine learning approaches for clusterizing students’ cognitive profile. Heliyon, 9(3), e14506. https://doi.org/10.1016/j.heliyon.2023.e14506
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830. https://jmlr.org/papers/v12/pedregosa11a.html
Pritasari, O. K., Marniati, M., & Susila, I. W. (2024). The effect of local potential-based workshop and entrepreneurship learning in increasing entrepreneurial interest. Jurnal Pendidikan Vokasi, 14(1), 1–11. https://doi.org/10.21831/jpv.v14i1.56910
Risal, A. A. N., Andayani, D. D., Suherman, M. I., & Kaswar, A. B. (2024). Utilizing the K-Means clustering algorithm for analyzing student achievement assessment at SMK Negeri 1 Gowa. Journal of Embedded Systems, Security and Intelligent Systems, 5(1), 60–67. https://doi.org/10.59562/jessi.v5i1.2178
Romero, C., & Ventura, S. (2020). Educational data mining and learning analytics: An updated survey. WIREs Data Mining and Knowledge Discovery, 10(3), e1355. https://doi.org/10.1002/widm.1355
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
Siregar, H. L., Hidayanthi, R., & Sakti, A. L. D. (2024). Implementation of K-Means clustering on student learning achievements based on social economic and social related. Research and Development in Education, 4(2), 1447–1459. https://doi.org/10.22219/raden.v4i2.36742
Susantiningrum, S., Siswandari, S., Joyoatmojo, S., & Mafruhah, I. (2023). Leveling entrepreneurial skills of vocational secondary school students in Indonesia: Impact of demographic characteristics. International Journal for Research in Vocational Education and Training, 10(1), 113–137. https://doi.org/10.13152/IJRVET.10.1.6
