Rapid urbanization and population growth have created significant challenges in urban mobility management, such as traffic congestion, inefficient public transportation, and environmental pollution. This paper presents the development and implementation of a Digital Twin (DT) platform aimed at addressing these issues within the context of smart mobility. The DT integrates a wide range of historical and real-time data, providing a holistic view of urban mobility conditions. Descriptive statistics are used to identify key patterns in parking occupancy and violations, while advanced Machine Learning (ML) and Deep Learning (DL) algorithms enhance predictive and generative analytics, forecasting parking demand and simulating various mobility scenarios. These insights, combined with visualization tools, map data onto the urban landscape, enabling spatial planning and resource allocation. Moreover, the integration of Generative Artificial Intelligence (GenAI) models significantly improves the platform's capability to generate realistic what-if scenarios, allowing urban planners to test different strategies in a virtual environment before implementing them in the real world. The results highlight the DT platform's potential to improve urban mobility management, especially in optimizing parking meter placement and enhancing user experience. While data availability limitations affect long-term prediction accuracy, the model demonstrates robustness and adaptability for extended forecasting, making it a valuable tool for smarter, more sustainable urban planning.