Demographic Segmentation of Election Supervisors Using K-Means Clustering

Kirei D.T Palar (Universitas Negeri Manado)
Irene R.H.T. Tangkawarouw (Universitas Negeri Manado)
Sondy C. Kumajas (Universitas Negeri Manado)

Journal of Embedded Systems, Security and Intelligent Systems
Vol 7 No 3 (2026): September 2026

Purpose – This study demonstrates the use of K-Means clustering for demographic segmentation of Indonesian election supervisors and proposes a dashboard-based analytical prototype for workforce profiling. The study responds to the absence of systematic, data-driven segmentation in supervisor development, training, mentoring, and resource allocation. Design/methods/approach – A quantitative data science workflow was applied, covering synthetic data generation, preprocessing, clustering, validation, stability testing, and dashboard development. Because formal requests for real supervisor-level demographic data from Bawaslu were denied due to privacy, consent, and re-identification concerns, the study used a synthetic dataset of 500 supervisors generated from publicly available institutional and demographic parameters. Four variables were used as clustering inputs: age, years of experience, gender, and education level. K-Means clustering was implemented with standardized features, and the optimal number of clusters was evaluated using the Elbow Method and Silhouette Score. Findings – The analysis identified three illustrative segments: junior-like, mid-level-like, and senior-like supervisor profiles. The optimal cluster solution was K=3, supported by the Elbow Method and a Silhouette Score of 0.38, indicating moderately well-defined clusters. Stability testing showed consistent results across multiple random seeds. The Streamlit dashboard successfully visualized demographic distributions, cluster profiles, and provincial dominance patterns. Research implications/limitations – The findings provide a methodological prototype only and should not be interpreted as empirical evidence about Bawaslu’s actual workforce. Originality/value – The study contributes by applying clustering to election supervisor segmentation, integrating geospatial dashboard visualization, and transparently documenting synthetic-data use when real administrative data access is restricted in a sensitive institutional context.