K-Means Clustering for Identifying Traffic Accident Hotspots in Depok City

Abstract

This study applies the K-Means clustering algorithm to support decision-making processes related to identifying traffic accident-prone areas in Depok City over a three-year period (2020-2022). Secondary data was obtained from the Traffic Accident Unit of the Depok Metro Police, encompassing monthly traffic accident recapitulations for each district. The data underwent preprocessing steps, including integration and selection of relevant attributes. Using RapidMiner, the data was clustered into three distinct groups, with the optimal number of clusters determined by the Davies-Bouldin Index (DBI), which yielded a score of 0.896, indicating a satisfactory clustering result. The findings reveal that four districts—Beji, Cimanggis, Pancoran Mas, and Sukmajaya—are identified as high-risk areas for traffic accidents. These results are expected to assist local authorities in implementing targeted safety measures. The study demonstrates that the K-Means clustering method is a viable tool for analyzing traffic accident data and can significantly contribute to improving road safety in urban areas