Data-driven logistics (R-8844)

Logistics involves different types of activities such as warehousing, transport, terminal operations and loading. Each of these activities involves various complex operational decisions which are often interrelated and subject to rapidly changing market conditions and environments. Therefore, good decision support software is essential for companies to remain competitive. Recent developments enabled logistics companies to digitally monitor and store data regarding their operations. Additionally, computational advances enabled software developers to implement advanced algorithms for optimising operational schedules. However, these two activities, monitoring and decision-making, currently represent two separate processes and only limited data is exchanged between them. This project seeks to develop innovative methodologies for data-driven optimisation in logistics. Such an approach would enable the use available data to learn and find patterns, thereby continuously and automatically adapting and improving logistics optimisation processes. Furthermore, it offers a stepping stone to solve complex interrelated problems in an integrated manner. This is expected to pave the way for a new generation of logistics optimization software, yielding substantial benefits over the rigid traditional methods. The developed techniques will be validated and evaluated on a number of case studies in different logistics contexts, thereby enabling an accurate assessment of the benefits of a data-driven approach to logistics decision-making.

Keywords:data science, logistics, machine learning, operations research, optimalisation

Disciplines:Applied economics, Economic history, Macroeconomics and monetary economics, Microeconomics, Tourism

Project type:Collaboration project