This study proposes a data-driven methodology for classifying Moroccan provinces based on seismic zoning criteria, specifically Peak Ground Velocity (PGV) and Peak Ground Acceleration (PGA). In the Introduction, an overview of earthquakes and seismic zoning is provided. The results section includes a detailed review of Principal Component Analysis (PCA), K-means clustering, and Hierarchical Clustering (AHC), discussing their theoretical foundations and implementation. In the case study, we evaluate the performance of individual clustering algorithms and hybrid clustering algorithms with PCA. In the discussion, we analyze performance indices obtained using cross-validation and quality metrics, showing that K-means clustering combined with PCA is the best approach. For cross-validation we found the average error intra-cluster (SSE), the standard deviation of intra-clusters distance, the average silhouette index, the calinski-harabasz index and davies-bouldin index are better compared to others. Additionally, we examine the sensitivity analysis and show that the model is not robust and we suggest future directions, including other parameters Geographic Information Systems (GIS) for enhanced seismic management and decision-making.