Data, the key ingredient in an optimized food supply

Smart industries logo

About the project

Buying whatever you want, when you want it, at a fair price: behold the miracle of the modern supermarket. To make this possible, retail companies, suppliers, and logistics partners need to work in perfect unison. Essential in achieving this is the ability to share and combine data across multiple ecosystems. AI4FoodLogistics has sunk its teeth into the challenge with a federated data ecosystem and new algorithmic techniques. 

Retail, and the food sector in particular, is a complex environment that requires close cooperation between multiple partners. At the same time, the sector continuously strives to increase efficiency and sustainability, e.g., by reducing waste.

Main challenges

To reach these goals, stakeholders need to overcome three main challenges:

  • Siloed data: although all organizations within the supply chain are connected, data often remains stored in silos within each separate company.
  • The Bullwhip Effect (BWE): continuous changes in consumer behavior and demand make forecasting sales, orders, and deliveries in retail extremely difficult. This effect is even more challenging when working with fresh, highly perishable foods.
  • Multiple variables and parameters: optimizing store operations or supply chain processes requires taking into account a vast range of ever-changing variables and parameters. In this context, human analysis and traditional analytics often provide suboptimal results.

Combined intelligence

To tackle these challenges, the AI4FoodLogistics consortium is exploring the following solutions:

  • Building a federated data ecosystem that brings together data from different stakeholders in the retail ecosystem. The resulting insights will enable optimized forecasting and the development of intelligent algorithms.
  • Improving store operations and increasing customer value while reducing food waste through hyper personalization based on new algorithmic techniques.
  • Enhancing the efficiency and sustainability of end-to-end, farm-to-fork supply chains through intelligent algorithms.

In-store testing

In this way, AI4FoodLogistics aims to reduce logistics overheads while delivering a premium, innovative, and personalized service for fresh food. To validate the outcomes of these research goals, forecasting capabilities and hyper-personalization will be tested in Delhaize stores and via Foodmaker’s customers. In addition, all industry partners will validate food logistics optimizations in a simulated environment that combines integrated data from supply chain partners and data generated by dynamic markdown and hyper-personalization models.

“AI4FoodLogistics will tackle food retail challenges by developing a reliable, just-in-time delivery experience for fresh food using a novel, ecosystem-spanning data architecture.”


AI For Food Logistics aims to achieve a highly reliable, just-in-time delivery experience for fresh food through end-to-end optimization of the logistics chain.

AI4FoodLogistics is an imec.icon research project funded by imec and Agentschap Innoveren & Ondernemen (VLAIO).

The project started on 01.09.2021 and is set to run until 31.08.2023.

Project information


  • Van Moer Logistics
  • Delhaize
  • Star Meal


  • imec - IDLab – UAntwerpen
  • imec - IDLab – UGent


  • Project lead: Sam Beelprez
  • Research lead: Siegfried Mercelis
  • Proposal manager: Siegfried Mercelis
  • Innovation manager: Annelies Vandamme