<p>This study utilizes the XGBoost model integrated with the Flatfile database, strong ground motion records derived from the Taiwan Strong Motion Instrumentation Program (TSMIP), to establish a crustal ground motion model (GMM) in forms of PGA, PGV, and spectral acceleration. When evaluating the performance of these models, particular attention is paid to the standard deviation of residuals and the R² score, as well as multiple analysis methods such as distance response, response spectra, and residual distribution to thoroughly assess the effectiveness and rationality of the models. Additionally, a key aspect of the methodology is the application of SHAP (SHapley Additive exPlanations) values to validate the importance of different predictors within our model. This approach not only clarifies the impact of various factors on strong ground motion but also highlights the interpretability of the model, addressing the traditional demands of engineering seismology for model rationality and explainability. Considering the imbalance in the earthquake dataset, especially lack of larger-scale and near-field events, the Smoter and Gaussian Noise (SMOGN) method is used for data augmentation. This method effectively balances the dataset, thereby enhancing the model to learn from rare but significant large-scale and/or near-field seismic events. The study also demonstrates the applicability of the model in seismic hazard assessment using the seismic hazard analysis software, incorporating our strong motion attenuation model for seismic motion simulation. The incorporation of machine learning techniques into the development of GMM marks a significant step forward in the advancement of seismic hazard assessment in Taiwan. This research could have a substantial impact on earthquake preparedness strategies, infrastructure resilience planning, and public safety protocols, demonstrating the potential of machine learning in engineering seismology.</p>