Integrating Self-Organizing Maps and K-Means in a Multidimensional Approach to Enhance Private University Market Segmentation

Amalia Nur Alifah, Wachda Yuniar Rochmah, Evellyn Verity Mesak

Abstract


Educational institutions face challenges in attracting prospective students while maintaining academic quality and resource efficiency. This study applies a hybrid approach that integrates Self-Organizing Maps (SOM) and K-Means to cluster schools based on four attributes, namely the number of accounts, average UTBK scores, geographical distance, and parental income. The analysis's findings produce three distinct clusters. With a high degree of attribute variation, Cluster 2 (279 schools) is a dominant group that suggests the possibility of extensive marketing campaigns. Clusters 1 (45 schools) and 3 (81 schools), on the other hand, are more uniform and call for a more specialized and focused strategy. These results imply that a data-driven approach can help institutions create interventions that are specific to each segment's profile and increase the efficacy of educational marketing strategies. In order to improve segmentation accuracy in the future, this study creates opportunities for investigating new features and dynamic clustering techniques.

Keywords


Data-Driven Decision Making; Educational Marketing; K-Means Clustering; School Segmentation; Self-Organizing Maps (SOM)

Full Text:

PDF

References


H. Khusnuliawati and D. R. Putri, “Hybrid clustering based on multi-criteria segmentation for higher education marketing,” TELKOMNIKA (Telecommunication Comput. Electron. Control., vol. 19, no. 5, pp. 1498–1506, 2021.

B. L. Ortiz, “Data Preprocessing Techniques for Artificial Learning (AI)/Machine Learning (ML)-Readiness: Systematic Review of Wearable Sensor Data in Cancer Care.,” JMIR Mhealth Uhealth, 2024.

Agnes Yonathan, “Indonesia Jadi Negara dengan Universitas Terbanyak Kedua di Dunia.” https://data.goodstats.id/statistic/indonesia-jadi-negara-dengan-universitas-terbanyak-kedua-di-dunia-Iab4A (accessed May 31, 2025).

W. A. Prastyabudi, A. N. Alifah, and A. Nurdin, “Segmenting the Higher Education Market: An Analysis of Admissions Data Using K-Means Clustering,” Procedia Comput. Sci., vol. 234, pp. 96–105, 2024.

P. D. dan T. Informasi, “Statistik Sekolah Menengah Atas (SMA) 2023/2024,” 2024.

M. Seyfried, S. Hollenberg, and J. Heße-Husain, “Student selection in higher education–the organisational performance dilemma,” J. High. Educ. Policy Manag., vol. 46, no. 6, pp. 671–686, 2024.

Y.-F. Chen and C.-H. Hsiao, “Applying market segmentation theory to student behavior in selecting a school or department.,” New Horizons Educ., vol. 57, no. 2, pp. 32–43, 2009.

M. Arpay, “Student Mining Using K-Means Clustering: A Basis for Improving Higher Education Marketing Strategies,” Psychol. Educ. A Multidiscip. J., vol. 14, no. 1, p. 1, 2023.

E. Xiao, “Comprehensive K-Means Clustering,” J. Comput. Commun., vol. 12, no. 3, pp. 146–159, 2024.

M. Z. Rodriguez et al., “Clustering algorithms: A comparative approach,” PLoS One, vol. 14, no. 1, p. e0210236, 2019.

Š. Brodinová, P. Filzmoser, T. Ortner, C. Breiteneder, and M. Rohm, “Robust and sparse k-means clustering for high-dimensional data,” Adv. Data Anal. Classif., vol. 13, pp. 905–932, 2019.

E. U. Oti, M. O. Olusola, F. C. Eze, and S. U. Enogwe, “Comprehensive review of K-Means clustering algorithms,” Criterion, vol. 12, pp. 22–23, 2021.

K. K. Jassar and K. S. Dhindsa, “Comparative study and performance analysis of clustering algorithms,” Int J Comput Appl, vol. 975, p. 8887, 2015.

V. Çetin and O. Yıldız, “A comprehensive review on data preprocessing techniques in data analysis,” Pamukkale Üniversitesi Mühendislik Bilim. Derg., vol. 28, no. 2, pp. 299–312, 2022.

C. Fan, M. Chen, X. Wang, J. Wang, and B. Huang, “A review on data preprocessing techniques toward efficient and reliable knowledge discovery from building operational data,” Front. energy Res., vol. 9, p. 652801, 2021.

I. Engdahl, “Agreements ‘in the wild’: Standards and alignment in machine learning benchmark dataset construction,” Big Data Soc., vol. 11, no. 2, p. 20539517241242456, 2024.

Y. Miftahuddin and A. R. S. Ridwan, “Application of Self-Organizing Map and K-Means to Cluster Bandwidth Usage Patterns in Campus Environment,” J. Online Inform., vol. 10, no. 1, pp. 66–76, 2025.

W. Hua and L. Mo, “Clustering Ensemble Model Based on Self‐Organizing Map Network,” Comput. Intell. Neurosci., vol. 2020, no. 1, p. 2971565, 2020.

N. Shi and R. Al Kontar, “Personalized pca: Decoupling shared and unique features,” J. Mach. Learn. Res., vol. 25, no. 41, pp. 1–82, 2024.

D. L. B. Fortela et al., “Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion,” Clean Technol., vol. 2, no. 2, p. 11, 2020.

A. Deshmukh, “Variational Quantum Self-Organizing Map,” arXiv Prepr. arXiv2504.03584, 2025.

G. T. Breard, “Evaluating self-organizing map quality measures as convergence criteria,” 2017.

J. Tian, M. H. Azarian, and M. Pecht, “Anomaly detection using self-organizing maps-based k-nearest neighbor algorithm,” in PHM society European conference, 2014, vol. 2, no. 1.

R. A. Sary, N. Satyahadewi, and W. Andani, “APPLICATION OF K-MEANS++ WITH DUNN INDEX VALIDATION OF GROUPING WEST KALIMANTAN REGION BASED ON CRIME VULNERABILITY,” BAREKENG J. Ilmu Mat. dan Terap., vol. 18, no. 4, pp. 2283–2292, 2024.

A. Pita, F. J. Rodriguez, and J. M. Navarro, “Analysis and Evaluation of Clustering Techniques Applied to Wireless Acoustics Sensor Network Data,” Appl. Sci., vol. 12, no. 17, p. 8550, 2022.

S. Myagmarsuren, “Exploring the Use of Silhouette Score in K-Means Clustering for Image Segmentation (Exploring the Use of Silhouette Score in K-Means Clustering for Image Segmentation),” vol. 13, no. 4, 2024, [Online]. Available: http://www.ijert.org




DOI: http://dx.doi.org/10.30829/zero.v9i1.24430

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Publisher :
Department of Mathematics
Faculty of Science and Technology
Universitas Islam Negeri Sumatera Utara Medan
📱 WhatsApp:085270009767 (Admin Official)
SINTA 2 Google Scholar CrossRef Garuda DOAJ