Analysis Of Population Data Grouping Using K-Means For Efficiency Data Centralization And Backup

Abstract

Population data management at the village level plays an important role in supporting administrative services, development planning, and data-driven decision-making. However, in many village offices, including the Bandar Sono Village Office, population data is still managed manually and stored in fragmented formats, resulting in inefficiencies in data retrieval, duplication risks, and difficulties in performing structured data backup. This condition indicates the need for a more systematic approach to organizing and analyzing population data. This study aims to analyze and implement the K-Means clustering algorithm to group population data in order to improve the efficiency of data centralization and backup processes. The research method used is quantitative, involving data collection, preprocessing, and clustering analysis using the K-Means algorithm based on attributes such as the number of male residents, female residents, and total population. The results show that the K-Means method successfully groups population data into three clusters, namely small, medium, and large population categories. These clustering results provide more structured and meaningful information, facilitating easier data analysis and improving the effectiveness of data management. In conclusion, the implementation of K-Means clustering contributes to enhancing the efficiency, organization, and reliability of population data management systems, thereby supporting better administrative services and decision-making at the village level.