The Massachusetts Institute of Technology (MIT) Center for Transportation & Logistics (CTL) and Mecalux have unveiled an advanced artificial intelligence-based simulator designed to optimise inventory distribution across multiple warehouses within logistics networks.
Named Genetic Evaluation & Simulation for Inventory Strategy (GENESIS), this platform leverages machine learning models to explore thousands of scenarios and determine optimal stock levels and replenishment strategies.
Dr. Matthias Winkenbach, director of research at the MIT CTL, explained the platform’s capabilities: “The genetic algorithm enables multiple simulations to be run using different parameters until the most efficient logistics strategy is identified. Companies can compare scenarios and select the one that best fits their operations.”
GENESIS considers various factors such as forecast demand in different regions, transport costs, and each warehouse's operational capacity to assess various inventory replenishment policies without impacting real-world operations.
Once the necessary data is inputted, the system generates an optimal solution along with comprehensive statistical dashboards. Users can access insights on consumption patterns, highly variable demand regions, SKUs susceptible to stockouts, and warehouses facing supply challenges.
A significant feature of GENESIS is its capacity to redistribute inventory among warehouses rather than simply ordering new products from suppliers. The simulator evaluates whether it might be more efficient to transfer goods from a facility with excess inventory, enabling companies to cut costs and better utilise existing stock.
In addition to inventory management, GENESIS assists in optimising transport logistics by suggesting whether to consolidate shipments or fulfil orders from specific locations to decrease delivery times and transport expenses.
Rodrigo Hermosilla, a research engineer at the MIT Intelligent Logistics Systems Lab, stated, “The real challenge wasn’t finding the right algorithm — it was making it fast enough to be practical. We developed GENESIS from the ground up to evaluate thousands of scenarios simultaneously... What used to take days now takes minutes.”
Unlike analytical tools limited to specialised users, GENESIS is accessible to both technical teams and business decision-makers. “The goal is to help companies minimise the total cost of their logistics network while ensuring the highest service level,” called out Javier Carrillo, CEO of Mecalux.
The collaboration between Mecalux and MIT CTL is set to expand, investigating further applications of AI in logistics processes, including internal replenishment, digital twins for automated storage systems, and slotting optimisation.
