First Friday Webinars – Courier-oriented route optimization for last-mile delivery at Deutsche Post

Traditional last-mile delivery planning purely based on optimization methods often lacks important real-life aspects and thus does not satisfy relevant operational requirements. Only experienced couriers have tacit knowledge about the delivery area and its customers, forcing them to deviate from planned routes. They know where to find good parking spots, when to best approach certain business customers, and which neighbors to approach at what times when the actual recipient is not at home. This tacit knowledge is almost impossible to collect and maintain, let alone to incorporate in optimization algorithms.

Thus, we at Deutsche Post DHL developed an algorithm following a different approach: We aim at implicitly learning about this tacit knowledge from historical tours and combine this with optimization algorithms to plan routes that an experienced courier would choose. In this talk we will present details of our algorithm, which incorporates machine learning, statistics, and optimization in a novel way. Furthermore, we show how it impacted last-mile delivery planning at Deutsche Post after its rollout across Germany.

About the speakers

Speaker Ugur Arikan is an Operations Research Scientist in the Data Analytics Center of Excellence at Deutsche Post DHL. He got his MSc and PhD degrees in Industrial Engineering at Middle East Technical University. His PhD and postdoc studies focused on airline disruption management and distributionally robust traffic equilibrium, respectively. He joined DPDHL after his postdoc at Singapore University of Technology and Design. Currently, he focuses on last-mile delivery and service network design projects within the team.

Speaker Jonas Witt is working as Operations Research Scientist in the Data Analytics Center of Excellence at Deutsche Post DHL, currently focusing on last-mile delivery and service network design projects. He has a B.Sc. and M.Sc. degree in Mathematics from RWTH Aachen University as well as a doctoral degree from RWTH Aachen University on decomposition methods for mixed-integer linear programming. Besides his operations research expertise, he gained experience working on more general data analytics projects as consultant.