Penerapan Algoritma K-Means Clustering pada Pengelompokkan Data Kriminal Menurut Kabupaten/Kota di Sumatera Utara Tahun 2022

Abstract

The high crime rate in North Sumatra province in 2022 made North Sumatra the second province with the highest crime rate in Indonesia. This study aims to apply the k-means clustering algorithm to crime data in regencies/cities in North Sumatra in 2022 by identifying the patterns and characteristics of the formed crime. The research data consists of crime data that occurred in North Sumatra province in 2022, collected from the publication of the Central Statistics Agency (BPS) of North Sumatra. The variables used in this study include theft, murder, rape, domestic violence (KDRT), fraud, and embezzlement. The k-means clustering method is a non-hierarchical data clustering method that divides data into groups. The results show that the clustering of regencies/cities in North Sumatra based on crime data that occurred in 2022 using the k-means clustering method produced 4 optimal iterations. With 3 clusters, the results show that cluster 1 contains one regency/city with a high crime rate, cluster 2 contains 5 regencies/cities with a moderate crime rate, and cluster 3 contains 23 regencies/cities with a low crime rate. An ANOVA test was also conducted, and the significance values for each variable were less than 0.05, indicating that the three clusters have significant differences.