Self-compacting concrete (SCC) has gained widespread application in infrastructure projects globally due to its self-consolidating properties, which eliminate the need for vibration, enhance workability, reduce labor costs, and provide excellent surface finish and durability. In recent years, the use of machine learning techniques to predict the compressive strength of SCC gained importance; however, these models often require further optimization for improved accuracy. This study presents hybrid models integrating empirical mode decomposition (EMD) with machine learning algorithms such as random forest (RF) and decision tree (DT). A comparative analysis showed that EMD preprocessing notably enhanced the performance of both RF and DT models. The EMD-DT model achieved the highest accuracy with a coefficient of determination (R2) of 0.9454, while the DT model without EMD preprocessing yielded a lower R2 value of 0.9069.