Penerapan Algoritma K-Means Clustering Dalam Menganalisis Tren Data Pemilih Di Kabupaten Seluma

Abstract

General elections are one of the main pillars of the democratic system in Indonesia. Voter turnout is an important indicator in assessing the success of elections. Seluma Regency shows variations in voter characteristics in each sub-district, in terms of number, gender, and age. This study aims to analyze voter participation trends by applying the K-Means Clustering algorithm to group regions based on similar voter characteristics. The data used includes the number of Permanent Voter Lists (DPT), age categories, and gender, obtained from the Seluma Regency General Election Commission (KPU) in 2024. The system was developed using the Waterfall method, with the Python programming language and the Flask framework. The clustering results show that of the 200 villages/subdistricts analyzed, 137 villages/subdistricts (68.5%) were included in the low cluster and 63 villages/subdistricts (31.5%) were in the high cluster. Although the number of villages/subdistricts in the low cluster is more dominant, the distribution of voters based on gender and age group is relatively balanced between the two clusters, with a slight tendency to be more concentrated in the high cluster. This information is expected to serve as a strategic basis for the KPU.in developing a more effective and targeted outreach program. System testing was conducted using the black box method to ensure that all functions ran according to plan.