MIT and Mecalux Build AI Simulator to Optimize Warehouse Inventory
MIT's Intelligent Logistics Systems Lab and warehouse technology company Mecalux have developed an AI-based platform that optimizes how inventory is distributed across multiple warehouses. The system, called GENESIS (Genetic Evaluation & Simulation for Inventory Strategy), analyzes thousands of scenarios in minutes to determine optimal stock levels and replenishment timing.
The simulator uses machine learning to test different inventory policies without affecting live operations. It accounts for regional demand forecasts, transportation costs, and warehouse capacity to generate recommendations that reduce logistics costs while maintaining service levels.
How It Works
GENESIS starts by accepting data on demand, costs, and operational constraints. The system then runs thousands of simultaneous scenario analyses-a computational approach that would take days using traditional sequential methods.
A key feature is inventory rebalancing. Instead of automatically ordering from suppliers, the tool first checks whether products can be transferred from other facilities with excess stock. This reduces unnecessary purchases and makes better use of existing inventory.
The platform also recommends transportation strategies, such as whether to consolidate shipments for cheaper truckloads or fulfill orders from specific locations to cut delivery times and costs.
Users see results through statistical dashboards showing consumption patterns, demand variability by region, stockout risks for specific products, and supply issues at individual warehouses.
Speed Changed the Equation
The engineering challenge wasn't selecting the right algorithm-it was making it fast enough for practical use. Researchers designed GENESIS to evaluate thousands of scenarios simultaneously rather than one at a time.
"What used to take days now takes minutes, which means companies can use it for real tactical planning, not just theoretical analysis," said Rodrigo Hermosilla, Research Engineer at MIT's Intelligent Logistics Systems Lab.
The platform targets both technical teams and business decision-makers, not just specialized analysts.
Part of Broader Collaboration
GENESIS is the first major output from a joint initiative between Mecalux and MIT's Center for Transportation & Logistics. The collaboration is expanding to other logistics processes, including internal replenishment, digital twins for automated storage systems, and slotting optimization.
Mecalux develops automated storage solutions, warehouse management software, and racking systems. The company operates 12 manufacturing plants, seven R&D centers, and employs more than 5,500 people globally.
For development teams building logistics software or working on supply chain optimization, understanding how AI can compress analysis timelines from days to minutes has direct relevance. Learn more about applying AI to operational challenges through AI for Operations or explore AI Data Analysis Courses that cover scenario modeling and statistical dashboards.
Your membership also unlocks:
