Skripsi
THE EXPERIENCES OF STUDENTS IN THE ENGLISH LANGUAGE EDUCATION STUDY PROGRAM AT SRIWIJAYA UNIVERSITY IN BALANCING PART-TIME WORK AND ACADEMIC RESPONSIBILITIES
Crime is a complex social problem that continues to increase in various regions of Indonesia. The increasing number of crime cases in Indonesia, particularly during the 2021 to 2023 period, indicates the need for a more in-depth analysis to identify crime patterns and crime-prone areas. This study aims to cluster provinces in Indonesia based on crime rates and to compare the performance of the K-Means and K-Medoids methods in the clustering process. The data used in this study consist of crime data from all provinces in Indonesia during the 2021 to 2023 period, where each province is represented based on each year of observation. The optimal number of clusters was determined using the Elbow, Silhouette Coefficient, and Davies-Bouldin Index (DBI) methods. The results showed that the optimal number of clusters was 2 clusters, namely clusters with low and high crime rates. The K-Means method produced better performance than the K-Medoids method with a DBI value of 0.838 and a Silhouette value of 0.6557, while the K-Medoids method produced a DBI value of 1.042 and a Silhouette value of 0.6107. In addition, the results indicated an increase in the number of provinces included in the high-crime cluster from 2021 to 2023. There were also provinces that consistently remained in the high-crime cluster, namely North Sumatra Province and DKI Jakarta Province during the observation period, indicating relatively high crime rates. Keywords: crime, clustering, K-Means, K-Medoids.