Opportunities for Machine Learning in Urban Logistics

There has been a paradigm-shift in urban logistic services in the last years; global interconnectedness, urbanization, ubiquitous information streams, and increased service-orientation raise the need for anticipatory real-time decision making. A striking example are logistic service providers: Service promises, like same-day or restaurant meal delivery, dial-a-ride, and emergency repair, force logistic service providers to anticipate future demand, adjust to real-time traffic information, or even incorporate unknown crowdsourced drivers to fulfill customer expectations. Data-driven, anticipatory approaches are required to overcome the challenges of such services. They promise to improve customer satisfaction through accurate predictions (e.g., via supervised learning), enhanced fleet control (e.g., via reinforcement learning), and identification of demand patterns and delivery scenarios (e.g., via unsupervised learning). Within this research project, we combine recent advances in machine learning with established methods from operations research to tackle present-day challenges in urban logistics.