<![CDATA[Unemployment among the productive-age population remains a significant issue in urban areas, particularly in Bekasi City, which recorded an open unemployment rate of 7.82% in August 2024—much higher than the national average of 4.91%. This study aims to classify productive-age unemployment using a machine learning approach with the K-Means Clustering algorithm to provide a more comprehensive understanding of unemployment patterns. This research adopts a quantitative approach with the use of SPSS version 25 and RapidMiner software. SPSS is used for validity, reliability, multicollinearity tests, optimal cluster determination, and ANOVA. Primary data were collected through a questionnaire distributed to 100 respondents, with 75 valid responses meeting the criteria (productive age, unemployed, and actively seeking employment). The research variables include age, education level, unemployment duration, perception of job opportunities, self-perception, and factors causing unemployment. The K-Means analysis resulted in three main clusters: the pessimistic cluster (low motivation), the neutral cluster (moderate perception), and the optimistic cluster (high motivation). Evaluation using ANOVA showed that the variables significantly differentiate between the clusters. These findings emphasize that productive-age unemployment is heterogeneous and requires cluster-based specific policies.]]>
Copyrights © 2025
