Analysis of the Impact of the Pre-Employment Card Program and Clustering of Unemployment Rates in West Java Using Spectral Clustering

The Pre-Employment Card Program is an initiative launched by the Indonesian government to enhance workforce skills and reduce unemployment. In West Java Province, where population density and socio-economic diversity are high, assessing the effectiveness of this program is particularly relevant. This study aims to cluster regions in West Java based on participation in the Pre-Employment Card Program and unemployment rates using the spectral clustering method, as well as to analyze the program’s impact on regional unemployment levels.The dataset consists of variables such as unemployment rate, labor force size, education level, and program participation, obtained from the Central Bureau of Statistics (BPS) and the official Pre-Employment Program website (2020–2024). The clustering results identified two primary groups: regions with high unemployment and low participation, and those with low unemployment and high participation. The clustering structure achieved a Silhouette Score of 0.2808, indicating a reasonably good cluster separation. Correlation analysis revealed a weak positive relationship between program participation and unemployment reduction (r = 0.34), with the strongest correlation observed among senior high school and vocational school graduates. Regions with high participation experienced a decrease in the average unemployment rate from 10.39% to 8.36%, while those with low participation saw a decline from 9.16% to 7.21%. These findings suggest that the Pre-Employment Card Program holds potential in contributing to unemployment reduction in West Java. Nonetheless, further policy support is required, taking into account factors such as educational background, access to training, and local socio-economic dynamics to optimize the program’s impact.