Implementation of K-Means Clustering and Weighted Products in Determining Crime-Prone Locations

Abstract

Crime is an act that violates the law. The number of criminal acts that occur becomes a social problem that makes the community and the police uneasy. Increasing the number of crimes is a problem in the social aspect. This research aims to build an information system to provide information on areas prone to a crime that can help the police to speed up the crime resolution process. The grouping process uses the k-means method used to classify based on the level of vulnerability of the area, grouping crime is a good strategy in improving crime prevention planning. In addition to the k-means clustering method, we also use the weighted product method which functions as a recommendation ranking for crime selection. The grouping results obtained from this study are that there is 1 very vulnerable area, 5 areas in the vulnerable category and 3 safe areas. While the weighted product method produces melatilor kudus city 'as a prone to beating areas with a score of 0.182093.

Sequential optimization of process and supply chains considering re-refineries for oil and gas circularity

“…The ideal number of clusters is determined through multiple analyses of k number clusters. The common applications of the k-mean clustering algorithm include identifying crime-prone areas [46], customer segmentation [47], and transport optimization [48], which further justify its applicability in this work.…”

“…Hence, the optimal solution is determined using the Google-developed linear algorithm (GLOP), a solver in OR-Tools by maximizing the F obj as shown in Eq. (46).…”

Profiling the Inequality of School Water, Sanitation, and Hygiene Facilities Among Indonesian Regions Using Cluster Analysis

“…As all of the variables incorporated were numerical variables (measured in interval or ratio scale), the K-Means clustering method was selected. As a method that was extensively administered due to its simplicity, K-Means clustering had been employed in profiling conditions utilizing variables such as the risk of spreading infectious disease (19), community welfare indicators (20), and crime rate (21)(22)(23). This study then became the first to administer the WASH availability variables derived from school sanitation indicators encompassing all regencies/cities in Indonesia.…”