HYBRID CLUSTERING-CLASSIFICATION UNTUK PERSONALISASI REKOMENDASI UNIT KEGIATAN MAHASISWA BARU
Article Sidebar
Read Counter : 11
Download : 2
Main Article Content
Abstract
Penelitian ini bertujuan membantu mahasiswa baru memilih Unit Kegiatan Mahasiswa (UKM) yang sesuai minat secara lebih akurat melalui pendekatan hybrid clustering-classification. Data diperoleh dari kuesioner PKKMB 2024, distandarisasi, dan selanjutnya dikelompokkan menggunakan algoritma K-Means untuk mengidentifikasi pola minat mahasiswa. Label klaster hasil pengelompokan ini ditambahkan sebagai fitur tambahan pada model klasifikasi Multinomial Logistic Regression (MLR) dan Random Forest (RF). Evaluasi kinerja model dilakukan dengan stratified k-fold cross-validation, mengukur akurasi, presisi, recall, dan F1-score. Selain itu, uji Chi-Square dan Cramer’s V digunakan untuk menganalisis kekuatan asosiasi antar variabel kategorikal. Hasil eksperimen menunjukkan model hybrid (MLR dan RF) meningkatkan akurasi rekomendasi dibandingkan model baseline tanpa informasi klaster. Klaster minat memberikan konteks tambahan yang memperbaiki interpretabilitas rekomendasi. Sistem prototipe telah siap diintegrasikan ke dashboard layanan kemahasiswaan.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This work is licensed under a Jurnal Komunikasi Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
References
[1] A. Nadhira Tsurayya, R. Febriana, and M. A. Wildan, “Peran Unit Kegiatan Mahasiswa (UKM) dan Konsep Kepemimpinan terhadap Pengembangan Diri Mahasiswa FEB UTM,” J. Adm. Kant., vol. 12, no. 2, pp. 158–173, 2024.
[2] T. Pipit Muliyah, Dyah Aminatun, Sukma Septian Nasution, Tommy Hastomo, Setiana Sri Wahyuni Sitepu, “Panduan Pengenalan Kehidupan Kampus bagi Mahasiswa Baru (PKKMB) 2024,” J. GEEJ, vol. 7, no. 2, 2024.
[3] N. Ailmi, Z. Saharuna, E. Tungadi, T. Elektro, P. Negeri, and U. Pandang, “Metode Klasifikasi Pada Aplikasi Pendukung Keputusan Untuk Pemilihan Unit Kegiatan Mahasiswa,” 2020.
[4] A. Fanani, S. Aminah, and F. E. Purwiantono, “Sistem Informasi Klasifikasi Minat Siswa Terhadap Ekstrakurikuler Untuk Pembinaan Lomba Dengan Metode K-Means Clustering,” Smatika J., vol. 13, no. 01, pp. 166–175, 2023, doi: 10.32664/smatika.v13i01.920.
[5] A. Mulyana, Y. Hermawan, and N. J. Saputri, “Penerapan Data Mining Menggunakan Algoritma K-Means Clustering Untuk Rekomendasi Pilihan Program Studi Pada Mahasiswa Baru (Studi Kasus di Institut Bisnis dan Informatika Kesatuan),” KERNEL J. Ris. Inov. Bid. Inform. dan Pendidik. Inform., vol. 5, no. 1, pp. 60–72, 2024, doi: 10.31284/j.kernel.2024.v5i1.7624.
[6] N. Drushchak, V. Tyshchenko, and N. Polyakovska, “Towards Responsible AI in Education: Hybrid Recommendation System for K-12 Students Case Study,” Proc. - 2025 IEEE/ACM Int. Work. Responsible AI Eng. RAIE 2025, pp. 61–68, 2025, doi: 10.1109/RAIE66699.2025.00015.
[7] N. Dwitiyanti, S. A. Kumala, and S. D. Handayani, “Comparative Study of Earthquake Clustering in Indonesia Using K-Medoids, K-Means, DBSCAN, Fuzzy C-Means and K-AP Algorithms,” J. RESTI, vol. 8, no. 6, pp. 768–778, 2024, doi: 10.29207/resti.v8i6.5514.
[8] Samidi, R. Y. Suladi, and D. Kusumaningsih, “Comparison of the RFM Model’s Actual Value and Score Value for Clustering,” J. RESTI, vol. 7, no. 6, pp. 1430–1438, 2023, doi: 10.29207/resti.v7i6.5416.
[9] D. Nastiti, “Peran Organisasi Mahasiswa Dalam Pembentukan Sikap Demokratis,” Prima Magistra J. Ilm. Kependidikan, vol. 4, no. 1, pp. 64–76, 2023, doi: 10.37478/jpm.v4i1.2433.
[10] Suparyati, E. Utami, and A. H. Muhammad, “Applying Different Resampling Strategies In Random Forest Algorithm To Predict Lumpy Skin Disease,” J. RESTI, vol. 6, no. 4, pp. 555–562, 2022, doi: 10.29207/resti.v6i4.4147.
[11] A. N. D. Andra and Z. K. A. Baizal, “E-commerce Recommender System Using PCA and K-Means Clustering,” J. RESTI, vol. 6, no. 1, pp. 57–63, 2022, doi: 10.29207/resti.v6i1.3782.
[12] M. H. M. Maruyama, L. W. Silveira, J. P. M. de Oliveira, I. Gasparini, and V. Maran, “Hybrid Recommender System for Educational Resources to the Smart University Campus Domain,” Int. Conf. Comput. Support. Educ. CSEDU - Proc., vol. 1, no. Csedu, pp. 47–56, 2023, doi: 10.5220/0011841900003470.
[13] M. Gagolewski, M. Bartoszuk, and A. Cena, “Are cluster validity measures (in) valid?,” Inf. Sci. (Ny)., vol. 581, pp. 620–636, 2021, doi: 10.1016/j.ins.2021.10.004.
[14] R. Ananda, Muhammad Zidny Naf’an, Amalia Beladinna Arifa, and Auliya Burhanuddin, “Recommendation System for Specialization Selection Using K-Means Density Canopy,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 1, pp. 172–179, 2020, doi: 10.29207/resti.v4i1.1531.
[15] A. N. A. Aldania, A. M. Soleh, and K. A. Notodiputro, “A Comparative Study of CatBoost and Double Random Forest for Multi-class Classification,” J. RESTI, vol. 7, no. 1, pp. 129–137, 2023, doi: 10.29207/resti.v7i1.4766.
[16] V. R. S. Nastiti, Y. Azhar, and R. S. Putri, “Logistic Regression Using Hyperparameter Optimization on COVID-19 Patients’ Vital Status,” J. RESTI, vol. 7, no. 3, pp. 681–687, 2023, doi: 10.29207/resti.v7n3.4868.
[17] M. Aucancela, A. G. Briones, and P. Chamoso, “Educational Recommender Systems: A Systematic Literature Review,” Barcelona Conf. Educ. 2023 Off. Conf. Proc., no. November 2023, pp. 933–951, 2023, doi: 10.22492/issn.2435-9467.2023.74.
[18] A. F. Mohamed Nafuri, N. S. Sani, N. F. A. Zainudin, A. H. A. Rahman, and M. Aliff, “Clustering Analysis for Classifying Student Academic Performance in Higher Education,” Appl. Sci., vol. 12, no. 19, 2022, doi: 10.3390/app12199467.
[19] J. C. Sanguino, O. Mariño, N. Cardozo, R. Manrique, and M. Linares-Vásquez, “A course hybrid recommender system for limited user information scenarios,” J. Educ. Data Min., vol. 14, no. 3, pp. 162–188, 2022, doi: 10.5281/zenodo.7304829.
[20] D. Ariatmanto and A. M. Rifai, “The Impact of Feature Extraction in Random Forest Classifier for Fake News Detection,” J. RESTI, vol. 8, no. 6, pp. 730–736, 2024, doi: 10.29207/resti.v8i6.6017.
[21] R. Ananda and Achmad Zaki Yamani, “Determination of Initial K-means Centroid in the Process of Clustering Data Evaluation of Teaching Lecturers,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 3, pp. 544–550, 2020, doi: 10.29207/resti.v4i3.1896.
[22] A. A. C. Rindu, R. Astriratma, and A. Zaidiah, “K-Means Algorithm Implementation for Project Health Clustering,” J. RESTI, vol. 7, no. 5, pp. 1064–1076, 2023, doi: 10.29207/resti.v7i5.5181.
[23] ل. ع. كيورك and س. ع. جلال, “Using Multinomial Logistic Regression Model To Predict The Most Important Factors Affecting In The Students’ Selection For Specialization In Secondary Level For Some Schools Erbil City,” مجلة جامعة كركوك للعلوم الإدارية والاقتصادية, no. October 2023, p. 1, 2023, doi: 10.32894/1913-013-002-001.
[24] I. Wardhana, M. Ariawijaya, V. A. Isnaini, and R. P. Wirman, “Gradient Boosting Machine, Random Forest and Light GBM for Classification of Dried Beans,” J. RESTI, vol. 6, no. 1, pp. 92–99, 2022, doi: 10.29207/resti.v6i1.3682.
[25] H. N. Pradani and F. Mahananto, “Studi Literatur Human Activity Recognition (HAR) Menggunakan Sensor Inersia,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 6, pp. 1193–1206, 2021, doi: 10.29207/resti.v5i6.3665.
[26] A. A. Mutezar and U. Salamah, “Pengembangan Sistem Manajemen Event Pameran Karya Mahasiswa Menggunakan Metode Extreme Programming,” J. RESTI, vol. 5, no. 4, pp. 809–819, 2021, doi: 10.29207/resti.v5i4.3249.