On Solving the On-Demand Grocery Delivery Problem

With the rise of digitalization, customer expectations, and urbanization rates in cities, on-demand commerce is proving to be very promising, because of the flexibility offered to its consumers. This flexibility reveals many challenges regarding the delivery times claimed by customers. In this work, we address a new MILP model for the on-demand grocery delivery problem that assigns time windows starting from sets of time windows filled by customers when they order their groceries, while minimizing the total routing costs. The proposed model was firstly assessed on realistic data from a hypermarket in the northern suburbs of Tunis, Tunisia. The promising results reveal outlines for future work.