A Data Mining Approach to Clustering Cases of Violence Against Children in Indonesia

Abstract

Violence against children in Indonesia remains a crucial issue that requires a data-driven approach for more targeted interventions. This study aims to cluster provinces in Indonesia based on the number of cases of violence and the types of violence committed, namely physical, psychological, and sexual violence. The method used in this study is the K-Means Clustering algorithm, an unsupervised learning technique in data mining that is able to find hidden patterns in large data sets. Data was obtained from the Ministry of Women's Empowerment and Child Protection's Gender and Child Information System (SIGA), which covers 38 provinces. The clustering results produced three main groups: a cluster with high levels of violence consisting of the provinces of North Sumatra, DKI Jakarta, West Java, Central Java, and East Java; a cluster with moderate levels of violence consisting of 16 provinces; and a cluster with low levels of violence covering 17 provinces. These findings are expected to form the basis for the development of evidence-based child protection policies geographically and thematically.