The growing adoption of wind turbines to generate electricity raises the need for more accurate WSP to understand the instability of WS and mitigate the negative effect caused by the random nature of WS in achieving optimal electricity production. This paper used the Machine Learning model (Random Forest Regression) to examine the effect of Empirical Mode Decomposition (EMD) application in feature extraction for WSP. The obtained datasets for this work were from a credible open-access website collected on tropical cities (Khota Bahru, KLIA Sepang, Kuantan, Muadzam Shah, and Pulau Langkawi) meteorological stations in Malaysia as case studies. The dataset underwent preparation before duplicating the dataset into a reference and extraction dataset, then applied Empirical Mode Decomposition (EMD) on the extraction dataset for all five case studies to decompose each feature of the extraction datasets respectively into five Intrinsic Mode Functions (IMFs) then, reconstructed the IMFs into separate columns as new variables and used the IMFs extracted datasets and the reference datasets for predictions. The model prediction accuracy and performance for both datasets were obtained and compared. After comparison, the EMD-extracted dataset predictions produced higher accuracy and lower errors than the actual dataset prediction for Khota Bahru, KLIA Sepang, Kuantan, Muadzam Shah and most effectively for Pulau Langkawi. In conclusion, Empirical Mode Decomposition (EMD) application improved the accuracy and model performance.