PEMETAAN TALENTA SISWA MENGGUNAKAN ALGORITMA K-MEANS CLUSTERING BERDASARKAN PRESTASI AKADEMIK DAN NON-AKADEMIK

Muhammad Munsarif; Muhammad Sam’an

doi:10.33506/insect.v12i2.5011

Authors

Muhammad Munsarif Program Studi Informatika, Universitas Muhammadiyah Semarang
Muhammad Sam’an Program Studi Informatika, Universitas Muhammadiyah Semarang

DOI:

https://doi.org/10.33506/insect.v12i2.5011

Keywords:

K-Means Clustering, pemetaan talenta, akademik, non-akademik

Abstract

Pemetaan talenta siswa merupakan langkah strategis untuk mendukung pengembangan sumber daya manusia unggul dalam rangka mewujudkan visi Indonesia Emas 2045. Selama ini proses identifikasi potensi siswa di sekolah sering dilakukan secara manual dan subjektif sehingga memerlukan waktu yang lama serta berpotensi menimbulkan bias dalam pengambilan keputusan. Penelitian ini bertujuan menerapkan algoritma K-Means Clustering untuk memetakan talenta siswa berdasarkan indikator akademik dan non-akademik secara lebih objektif. Penelitian menggunakan data simulasi (dummy) yang dirancang untuk merepresentasikan karakteristik umum data siswa di lingkungan sekolah. Data akademik meliputi nilai Tes Potensi Akademik dan rata-rata rapor, sedangkan data non-akademik mencakup prestasi olahraga, seni, dan kepemimpinan, yang seluruhnya dinormalisasi ke dalam skala 0–1 agar setiap variabel memiliki kontribusi yang seimbang dalam proses klasterisasi. Penentuan jumlah klaster optimal dilakukan menggunakan metode Elbow dan Silhouette Score, sedangkan kualitas klaster dievaluasi menggunakan Silhouette Score, Davies–Bouldin Index (DBI), dan Calinski–Harabasz Index (CHI). Hasil penelitian menunjukkan bahwa jumlah klaster optimal adalah K = 3 dengan Silhouette Score sebesar 0,45, DBI sebesar 1,32, serta nilai CHI yang lebih tinggi dibandingkan konfigurasi lainnya. Tiga klaster yang terbentuk menunjukkan karakteristik yang berbeda, yaitu kelompok siswa dengan capaian akademik tinggi namun prestasi non-akademik rendah, kelompok dengan dominasi prestasi non-akademik disertai capaian akademik sedang, serta kelompok dengan profil relatif seimbang antara akademik dan non-akademik. Temuan ini menunjukkan bahwa penerapan K-Means Clustering mampu mengurangi subjektivitas dalam pemetaan talenta siswa serta memberikan dasar analisis yang lebih objektif bagi pihak sekolah dalam merancang program pembinaan akademik maupun non-akademik yang lebih tepat sasaran.

References

[1] M. A. Al-Barrak and M. S. Al-Razgan, “Predicting students’ performance through classification: A case study,” J. Theor. Appl. Inf. Technol., vol. 75, no. 2, pp. 167–175, 2015.

[2] L. Aulck, N. Velagapudi, J. Blumenstock, and J. West, “Predicting Student Dropout in Higher Education,” 2017. [Online]. Available: http://arxiv.org/abs/1606.06364

[3] Z. Papamitsiou and A. A. Economides, “Learning Analytics and Educational Data Mining in Practice: A Systematic Literature Review,” Comput. & Educ., vol. 71, pp. 20–36, 2014, [Online]. Available: https://doi.org/10.1016/j.compedu.2013.10.003

[4] G. S. J. d. B. Siemens, “Learning Analytics and Educational Data Mining: Towards Communication and Collaboration,” in ACM International Conference Proceeding Series, 2017, vol. Part F1305, pp. 252–254.

[5] A. P. a-Ayala, “Educational data mining: A survey and a data mining-based analysis of recent works,” Expert Syst. Appl., vol. 41, no. P1, pp. 1432–1462, 2014, [Online]. Available: http://dx.doi.org/10.1016/j.eswa.2013.08.042%0Apapers3://publication/doi/10.1016/j.eswa.2013.08.042

[6] R. Baker and G. Siemens, Educational data mining and learning analytics. 2014. doi: 10.1017/CBO9781139519526.016.

[7] Tri Martuti, Eviana Tjatur Putri, and R. Gusmana, “Application of K-Means Clustering for Student Class Division System,” J. Big Data Anal. Artif. Intell., vol. 6, no. 2, pp. 17–24, 2023, doi: 10.71302/jbidai.v6i2.35.

[8] I. Singh, A. S. Sabitha, and A. Bansal, “Student performance analysis using clustering algorithm,” in Proceedings of the 2016 6th International Conference - Cloud System and Big Data Engineering, Confluence 2016, 2016, pp. 294–299. doi: 10.1109/CONFLUENCE.2016.7508131.

[9] N. Varela et al., “Student performance assessment using clustering techniques,” Commun. Comput. Inf. Sci., vol. 1071, pp. 179–188, 2019, doi: 10.1007/978-981-32-9563-6_19.

[10] M. Abdous, W. He, and C. J. Yen, “Using data mining for predicting relationships between online question theme and final grade,” Educ. Technol. Soc., vol. 15, no. 3, pp. 77–88, 2012.

[11] M. Sani Ibrahim, “Learning Style Detection Using K-Means Clustering,” Fudma J. Sci., vol. 4, no. 3, pp. 375–381, 2020, doi: 10.33003/fjs-2020-0403-351.

[12] A. M. Shahiri, W. Husain, and N. A. Rashid, “A Review on Predicting Student’s Performance Using Data Mining Techniques,” in Procedia Computer Science, 2015, vol. 72, pp. 414–422. doi: 10.1016/j.procs.2015.12.157.

[13] S. J. Sultan Alalawi, I. N. Mohd Shaharanee, and J. Mohd Jamil, “CLUSTERING STUDENT PERFORMANCE DATA USING k-MEANS ALGORITHMS,” J. Comput. Innov. Anal., vol. 2, no. 1, pp. 41–55, 2023, doi: 10.32890/jcia2023.2.1.3.

[14] J. W. Teunissen et al., “A machine learning approach for the classification of sports based on a coaches’ perspective of environmental, individual and task requirements: A sports profile analysis,” J. Sports Sci., vol. 43, no. 1, pp. 23–32, 2025, doi: 10.1080/02640414.2023.2271706.

[15] D. Kuswandi, E. Surahman, Z. Z. A. Thaariq, and M. Muthmainnah, “K-Means Clustering of Student Perceptions on Project-Based Learning Model Application,” in 2018 4th International Conference on Education and Technology, ICET 2018, 2018, pp. 9–12. doi: 10.1109/ICEAT.2018.8693932.

[16] C. Agusniar, S. Mulya Ulfa, and H. Rhomadhona, “Utilizing K-Means Clustering for Grouping Student Achievement Data to Evaluate Learning Activeness,” J. Adv. Comput. Knowl. Algorithms, vol. 2, no. 3, pp. 56–59, 2025, doi: 10.29103/jacka.v2i3.22591.

[17] T. M. . Facca and S. J. . Allen, “Using Cluster Analysis to Segment Students Based on Self-Reported Emotionally Intelligent Leadership Behaviors.,” J. Leadersh. Educ., vol. 10, no. 2, pp. 72–96, 2011, [Online]. Available: https://search.ebscohost.com/login.aspx?direct=true&db=eue&AN=88906207&site=ehost-live

[18] A. Narimani and E. Barberà, “Clustering Students Based on Online Learning Interactions Using Social Network Analysis,” Int. J. Emerg. Technol. Learn., vol. 20, no. 02, pp. 36–50, 2025, doi: 10.3991/ijet.v20i02.54517.

[19] S. R. Sobral and C. F. de Oliveira, “Clustering Algorithm to Measure Student Assessment Accuracy: A Double Study,” Big Data Cogn. Comput., vol. 5, no. 4, 2021, doi: 10.3390/bdcc5040081.

[20] S. R. Rahman, M. A. Islam, P. P. Akash, M. Parvin, N. N. Moon, and F. N. Nur, “Effects of co-curricular activities on student’s academic performance by machine learning,” Curr. Res. Behav. Sci., vol. 2, 2021, doi: 10.1016/j.crbeha.2021.100057.

[21] L. Pamungkas, N. A. Dewi, and N. A. Putri, “Classification of Student Grade Data Using the K-Means Clustering Method,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 13, no. 1, pp. 86–91, 2024, doi: 10.32736/sisfokom.v13i1.1983.

[22] C. Ke Ting, N. Ibrahim, S. H. Huspi, and W. M. N. Wan Kadir, “Multidimensional Context Clustering to Analyse Student Engagement in Online Learning Environment,” Int. J. Innov. Comput., vol. 14, no. 2, pp. 89–96, 2024, doi: 10.11113/ijic.v14n2.487.

[23] M. Ashok, “Machine Learning Algorithms for Personalized Learning Paths,” Int. Res. J. Mod. Eng. Technol. Sci., vol. 06, no. 03, pp. 211–218, 2024, doi: 10.56726/irjmets49965.

[24] O. Darcan and B. Badur, “Student Profiling on Academic Performance Using Cluster Analysis,” J. e-Learning High. Educ., pp. 1–8, 2012, doi: 10.5171/2012.622480.

[25] M. Alan and M. Temz, “A Study On Profiling Students via Data Mining,” Alphanumeric J., vol. 7, no. 2, pp. 239–248, 2019, doi: 10.17093/alphanumeric.630866.