Transportation data in a smart city environment is increasingly becoming available. This data availability allows building smart solutions that are viewed as meaningful by both city residents and city management authorities. Our research work was based on Lisbon mobility data available through the local municipality, where we integrated and cleaned different data sources and applied a CRISP-DM approach using Python. We focused on mobility problems and interdependence and cascading-effect solutions for the city of Lisbon. We developed data-driven approaches using artificial intelligence and visualization methods to understand traffic and accident problems, providing a big picture to competent authorities and supporting the city in being more prepared, adaptable, and responsive, and better able to recover from such events.
