In the last years, the arrival and progressively gained maturity of technological paradigms such as Connected Vehicles, the Internet of Things, Sensor Networks, Urban Computing, Smart Cities, Cloud Computing, Edge Computing, Big Data and others alike have ignited the role historically played by data-based learning techniques to levels never seen before. This sharp increase has been particularly noticed in the design and management of intelligent systems for transportation and mobility, as processes, services and applications deployed in these systems are fed with data substrates captured at unprecedented rates and scales. Legacy sensing equipment installed on the roads’ infrastructure (e.g., induction loops and cameras) are nowadays complemented by alternative means to sense the transportation and mobility context of interest in real time and ubiquitously, as can be exemplified by data collected in a crowd-sourced way by using ad-hoc smart applications, as well as floating car data and/or social media.