The Utilization of Information System for Crime Rate Modelling in Surabaya Using K-means

Abstract

This study aims to model the crime rate in the city of Surabaya using the k-means clustering method. The data used is crime data that occurred in Surabaya in previous years, which includes the type of crime, location of crime, and crime rate. The k-means clustering method is used to classify crime data in the Surabaya area for 2020-2022 consisting of cluster 3, namely areas with moderate crime rates covering 6 sub-districts (1,260 cases), cluster 1 with areas with high crime rates, namely 12 sub-districts with 2,363 cases, and cluster 2 areas with low crime rates consisting of 13 districts with 2,178 cases based on data on the number of crimes. The geospatial visualization system is used to visually display modeling results, making it easier for interested parties to identify the location of a crime. The results of this study are expected to provide useful information for interested parties, such as the police and the community, in taking preventive action regarding crime rates in Surabaya.