Descriptive Analysis Of K-Means and Apriori Methods To Find Promotion Strategies For University Bhayangkara.

Sultan Bacharuddin Yusuf hidayat; Tb. Ai. Munandar

doi:10.58776/ijitcsa.v2i3.151

Authors

Sultan Bacharuddin Yusuf hidayat Universitas Bhayangkara Jakarta Raya
Tb. Ai. Munandar Universitas Bhayangkara Jakarta Raya

DOI:

https://doi.org/10.58776/ijitcsa.v2i3.151

Keywords:

Segmentation, Associative Analysis, Data Mining, K-means, Apriori, Promotion Strategy

Abstract

The increasing number of higher education institutions in Indonesia has intensified competition between universities. Universitas Bhayangkara Jakarta Raya (Ubhara Jaya) must develop an effective marketing plan to stand out. This study used segmentation and associative analysis on 2023 student enrolment data. The Apriori algorithm identified patterns in student preferences for study programmes, while the K-Means method categorized students based on demographics and family income. Three income-based clusters were identified: C0 ‘Already stable’ (IDR 1,000,000 - 2,500,000), C1 ‘Focus on promotion strategy’ (IDR 20,000,000), and C2 ‘Maximise promotion again’ (IDR 5,000,000 - 10,000,000). The Davies-Bouldin Index (DBI) indicated k=5 as the optimal cluster number, but k=3 was adequate with a minimal score difference. The most popular programmes were Communication Science and Management, with high support and confidence values. This data helps Ubhara Jaya manage study programme demand and room availability. Combining K-Means and Apriori algorithms is expected to enhance data segmentation[1] and support effective marketing strategies, aiding strategic decisions in higher education marketing.

References

P.-Y. Dolbec, “Digital marketing strategy,” Digit. Mark. Strateg., pp. 1–245, 2021, doi: 10.4337/9781035311316.

Kemendikbud, “Statistik Pendidikan Tinggi (Higer Education Statistic) 2020,” PDDikti Kemendikbud, vol. 5, pp. 81–85, 2020, [Online]. Available: https://pddikti.kemdikbud.go.id/publikasi

A. Abriyanto and N. Damastuti, “Segmentasi Mahasiswa Dengan ‘Unsupervised’ Algoritma Guna Membangun Strategi Marketing Penerimaan Mahasiswa,” Insa. Comtech Inf. Sci. Comput. Technol. J., vol. 4, no. 2, pp. 10–18, 2019, [Online]. Available: http://ejournal.unira.ac.id/index.php/insand_comtech/article/view/677

E. H. Pujiarini, “Analisis Asosiasi Untuk Menentukan Strategi Promosi Perguruan Tinggi Dengan Algoritma Apriori,” J. Inform. dan Komput., vol. 4, no. 1, pp. 45–51, 2019.

O. Maimon and L. Rokach, Data Mining and Knowledge Discovery Handbook, Second. 2010.

D. Sugianti, H. Wim Hapsoro, and W. Setianto, “Penerapan Machine Learning Untuk Penentuan Segmentasi Mahasiswa Baru Dengan Metode K Modes,” IC-Tech, vol. 17, no. 1, pp. 1–9, 2022, doi: 10.47775/ictech.v17i1.227.

N. A. Rahmalinda and A. Jananto, “Penerapan Metode K-Means Clustering Dalam Menentukan Strategi Promosi Berdasarkan Data Penerimaan Mahasiswa Baru,” J. Tekno Kompak, vol. 16, no. 2, pp. 163–175, 2022.

H. Hairani, D. Susilowati, I. Puji Lestari, K. Marzuki, and L. Z. A. Mardedi, “Segmentasi Lokasi Promosi Penerimaan Mahasiswa Baru Menggunakan Metode RFM dan K-Means Clustering,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 21, no. 2, pp. 275–282, 2022, doi: 10.30812/matrik.v21i2.1542.

Y. Wicaksono, U. Nendra Pratama, S. Nurhasanah, T. Utari Ramadania, and W. Juslan, “Pemetaan Strategi Promosi Penerimaan Mahasiswa Baru Menggunakan K-Means,” Syst. Inf. Syst. Informatics J., vol. 7, no. 1, pp. 42–48, 2021, doi: 10.29080/systemic.v7i1.1268.

F. N. Nasari, “Algoritma A Priori Dalam Pengelompokkan Data Pendaftaran Mahasiswa Baru,” J. Sains dan Ilmu Terap., vol. 4, no. 1, pp. 40–45, 2021, doi: 10.59061/jsit.v4i1.102.

I. P. Astuti, “Algoritma Apriori Untuk Menemukan Hubungan Antara Jurusan Sekolah Dengan Tingkat Kelulusan Mahasiswa,” J. Tek. Inform., vol. 12, no. 1, pp. 69–78, 2019, doi: 10.15408/jti.v12i1.10525.

H. Kusumo, E. Sediyono, and M. Marwata, “Analisis Algoritma Apriori untuk Mendukung Strategi Promosi Perguruan Tinggi,” Walisongo J. Inf. Technol., vol. 1, no. 1, p. 49, 2019, doi: 10.21580/wjit.2019.1.1.4000.