The Massachusetts Institute of Technology (MIT) and Mecalux have created an AI-based simulator for warehouses in a logistics network, aiming to optimize inventory and transport at minimal cost without incurring stockouts.
Developed by MIT’s Center for Transportation & Logistics in partnership with Mecalux, the platform – Genetic Evaluation & Simulation for Inventory Strategy, or GENESIS – uses advanced machine learning models to test inventory replenishment policies without impacting real-world operations.
It analyzes possible scenarios based on regional forecast demand, transport costs, the operational capacity of each warehouse, and more. From here, it suggests the optimal stock level at each warehouse and flags when replenishment should take place.
Using data and variables entered into the system, GENESIS generates advanced statistical dashboards and allows both technical teams and business decision-makers to gauge consumption patterns, regional variations in demand, stockout risks between SKUs, and supply issues at warehouses, among other indicators.
“The genetic algorithm enables multiple simulations to be run using different parameters until the most efficient logistics strategy is identified,” explains Dr. Matthias Winkenbach, director of Research at the MIT Center for Transportation & Logistics and the Intelligent Logistics Systems Lab. “Companies can compare scenarios and select the one that best fits their operations.”
Users are alerted when it would be more efficient to ship products from another facility’s excess inventory, rather than automatically placing new orders with suppliers. This is expected to make full use of existing stock, rebalance inventory in warehouses across the network, and cut down on costs.
Additionally, the system can recommend methods of transport – for example, whether specific orders can be fulfilled from a particular location to reduce costs and delivery times, or whether shipments should be consolidated to optimize truckloads.
“The real challenge wasn’t finding the right algorithm — it was making it fast enough to be practical,” says Rodrigo Hermosilla, Research Engineer at the MIT Intelligent Logistics Systems Lab. “We developed GENESIS from the ground up to evaluate thousands of scenarios simultaneously rather than sequentially. What used to take days now takes minutes, which means companies can use it for real tactical planning, not just theoretical analysis.”
“The goal is to help companies minimise the total cost of their logistics network while ensuring the highest service level,” adds Javier Carrillo, CEO of Mecalux.
Mecalux and MIT’s Center for Transportation & Logistics are entering a new phase of collaboration. Together, they plan to expand the use of AI in logistics processes like internal replenishment, slotting optimization, and digital twins in high-density automated storage systems.
In a similar initiative, PepsiCo has announced a multi-year collaboration with Siemens and NVIDIA to transform its plant and supply chain operations through advanced digital twin technology and AI. Digital twins will be applied to reshape how plant and warehousing facilities are digitally simulated and tested, with early pilots underway in the United States.
A report from The Consumer Goods Forum’s Plastic Waste Coalition of Action has also argued that artificial intelligence can help companies generate and optimize packaging design, sort waste effectively, and trace materials throughout the supply chain.
If you liked this story, you might also enjoy:
The ultimate guide to packaging innovation in 2026
Packaging and Packaging Waste Regulation: what to know in 2026
Everything you need to know about global packaging sustainability regulation
No comments yet