MIT CTL, Mecalux develop an AI-based simulator to optimize inventory across warehouses

The Massachusetts Institute of Technology (MIT) Center for Transportation & Logistics and Mecalux said they have developed an artificial intelligence-based simulator capable of optimizing inventory distribution across different warehouses within the same logistics network.

MIT CTL and Mecalux said that the platform, called Genetic Evaluation & Simulation for Inventory Strategy (GENESIS), uses advanced machine learning models to analyze thousands of possible scenarios and determine the optimal stock level at each warehouse and when replenishment should occur.

AI handles variability across warehouses

The AI-based simulator accounts for variables such as forecasted demand in each region, transportation costs and the operational capacity of each warehouse to test various inventory replenishment policies without affecting real-world operations.

“The genetic algorithm enables multiple simulations to be run using different parameters until the most efficient logistics strategy is identified,” said 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.”

Once data and variables are entered into the system, MIT CTL and Mecalux said that GENESIS generates the optimal option along with advanced statistical dashboards. Users can analyze indicators such as consumption patterns, regions with high demand variability, SKUs with a greater risk of stockouts or warehouses experiencing supply issues.

Redistribute before purchasing

MIT CTL and Mecalux said that one of the system’s key features is its ability to rebalance inventory across warehouses. Instead of automatically placing new orders with suppliers, the tool analyzes whether it is more efficient to transfer products from another facility within the network where excess inventory is available. In this way, companies can reduce costs and make better use of existing stock.

“The real challenge wasn’t finding the right algorithm - it was making it fast enough to be practical,” said 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 system also recommends how to organize transportation. For example, MIT CTL and Mecalux said that it suggests whether shipments should be consolidated to optimize truckloads, or whether specific orders should be fulfilled from a particular location to reduce delivery times and costs.

“The goal is to help companies minimize the total cost of their logistics network while ensuring the highest service level,” said Javier Carrillo, CEO of Mecalux.

The organizations said that the AI-powered simulator is one of the first tangible results of the joint initiative between Mecalux and MIT CTL.

The collaboration is now entering a new phase focused on expanding the application of AI to other logistics processes, such as internal replenishment, digital twins in high-density automated storage systems and slotting optimization.