<![CDATA[Indonesia is undergoing a positive development, marked by an increase in the productive population and economic capacity over the past two decades. With the vision of "Golden Indonesia 2045," Indonesia aims to boost development across various sectors, including employment, by reducing unemployment and increasing female participation in the labor market. However, the demographic bonus presents both opportunities and challenges, potentially increasing productivity but also risking higher unemployment. This study uses machine learning to evaluate and analyze unemployment risk based on demographics, education, training, and pre-employment program participation. Using data from the National Labor Force Survey (SAKERNAS), the study applies models such as Random Forest, Gradient Boosting, Extreme Gradient Boosting, and KNearest Neighbor. The results show that while these models struggle to predict unemployment risk, they perform well in predicting employment status. Education level and marital status are significant predictors, while the pre-employment program does not significantly reduce unemployment risk.]]>
Copyrights © 2024
