When food complexity logistics become clear.

FoxyFoodDelivery is a service allowing to order food from several different restaurants with reduced delivery costs. The innovation relies on a multi-objective optimization algorithm able to mutualise the different neighbouring orders and to plan the tasks in an optimal way. Restaurants increases their margin, deliverymen have more flexibility in working hours, final clients have more choices for lower prices.

Many competitors in this huge market share a common point: the whole process, from ordering to delivery at the client's place, is not autonomously treated. The part of human interactions, at many different levels, is important and leads to decisions that are not optimal. Consequently this poor organisation leads to a waste of time, and so the cost of the delivery is still important. Our goal was to completely remove the human decision factor, using instead an algorithm based on Multi-Objective Optimization in order to organise the full process of delivery.

In October 2017, so 9 months after project starting, we were able to proceed to trials with 60 reals customers, 7 partner restaurants, and 4 runners to deliver orders. We have been in production mode during 9 days, for 11 services including lunch time, evening meals, during the week and also the week-end. Our goal was to test our modelling and complete logistics under representative commercial conditions. Runners were riding Geneva state, on electric bikes with a cart holding two insulated boxes, for hot and cold dishes. The video below shows some recordings done during a full delivery session.


After a second successful trial at the end of the project, in July 2018, the full project has been transfered to our partner Novag SA that runs now the project under the name Yumy.