<![CDATA[Divorce is a complex social phenomenon that continues to increase in Indonesia. Based on data from 34 provinces, divorce is influenced by various factors, both internal and external to the household. This research aims to describe the main factors causing divorce based on national data and review relevant literature using machine learning methods, especially unsupervised learning techniques in the form of clustering. The dominant factors found include constant disputes and arguments, economic problems, domestic violence, abandonment of one of the parties, and infidelity. This research uses K-Means and DBSCAN algorithms to compare the results. It is known that the best modeling with Silhoutte Score comparison is DBSCAN of 0.331. DBSCAN with optimal clusters was obtained from a combination of epsilon parameter 2.9 and minimum sample 2. The clustering results were then further analyzed to evaluate the data distribution and identify the dominant characteristics in each cluster. These findings indicate the need for a multidisciplinary approach in understanding and addressing divorce issues in Indonesia in order to reduce the divorce rate and improve the quality of family life.]]>
Copyrights © 2025
