Impact pile driving generates ground vibration that causes discomfort to neighboring occupants and workers, and damages to nearby sensitive equipment and structures, highlighting the need of vibration monitoring during pile driving. Despite advancements in latest technologies, vibration monitoring is performed manually, which is not always practical and efficient due to the dynamic and hazardous nature in construction site environment. The objective of this study is to integrate machine learning (ML) algorithms, for prediction of ground vibration propagation. Methodology consists of selecting a construction site, FEM model development and validation, vibration data extraction, and ML model training and evaluation. Potential of Artificial Neural Network (ANN), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Decision Tree (DT), Support Vector Regression (SVR) and Random Forest (RF) as ML tools were studied. The results demonstrate precision of vibration prediction with ML technology, that can be used for predictions of ground vibration propagation.