<![CDATA[The increasing number of Indonesian migrant workers distributed across various destination countries has created a need for data-driven analysis to better understand migrant worker distribution patterns and support effective policy formulation. This study aims to analyze the characteristics and patterns of Indonesian migrant workers in Cianjur Regency using a data mining approach with the K-Means Clustering algorithm. The dataset used was obtained from Indonesian migrant workers placement data based on destination countries and processed through the Knowledge Discovery in Databases stages, including data selection, preprocessing, transformation, clustering, and evaluation. The clustering process was carried out using the K-Means algorithm, while the optimal number of clusters was determined using the Elbow Method and validated using the Silhouette Score. The results showed that the optimal number of clusters was 2 clusters with a Silhouette Score value of 0.849, indicating good clustering quality. The first cluster was dominated by destination countries with high numbers of migrant workers, while the second cluster consisted of countries with relatively lower numbers of migrant workers. These findings are expected to support data-driven decision-making for migrant worker placement policies.]]>
Copyrights © 2026
