Mapping of K-Means Clustering Crime Prone Areas in Brebes Regency

Abstract

This research aims to map crime-prone areas in the Brebes Police area using the K-Means Clustering method. The crime data used in this research was collected from weekly police reports in the Brebes Police area during 2023. The K-Means Clustering method was chosen because of its ability to group data based on similar characteristics, making it easier to identify crime patterns in various areas. The data was analyzed using rapidminer software to perform clustering, and the results were visualized in the form of a web-based interactive map developed using Visual Studio. The clustering results show that the Brebes area can be categorized into three levels of vulnerability: moderately vulnerable, vulnerable and very vulnerable. This mapping provides a clear picture of the distribution of crime rates in various regions, helping the police in designing more effective and efficient handling strategies. The system developed also provides features for accessing detailed data regarding the type and frequency of criminal acts in each area, which can be used by the Brebes Police and the general public. The implementation of this system is expected to increase the efficiency of crime data management, facilitate access to information, and support more targeted preventive and enforcement efforts. In addition, with information that is more structured and easily accessible, people can be more aware of potential threats in their surrounding environment. This research shows that the use of technology in managing crime data can make a significant contribution to increasing security and order in society. The web application system for mapping crime-prone areas using K-Means Clustering in the Brebes Police area was successfully developed and implemented, providing accurate and useful information for efforts to prevent and handle crime.