Balancing inventory across a distributed network has long forced companies to choose between excess stock and missed service levels. A new AI-driven simulator from MIT and warehouse automation firm Mecalux aims to shift that equation by allowing planners to test thousands of inventory and transport configurations before committing capital or capacity.
Researchers at the MIT Center for Transportation & Logistics (CTL), working through the Intelligent Logistics Systems Lab, have partnered with Mecalux to develop Genetic Evaluation & Simulation for Inventory Strategy, known as GENESIS. The platform uses a genetic algorithm to evaluate thousands of possible combinations of inventory positioning, replenishment timing, and transportation flows across multiple facilities.
The objective is straightforward: lower total logistics costs while protecting service levels and reducing the risk of stockouts. GENESIS ingests operational data, including demand forecasts, facility constraints, and transportation costs, then simulates alternative strategies in a controlled environment. Because the scenarios run outside live operations, companies can stress-test network decisions without exposing service performance to disruption.
Rebalancing Before Reordering
A distinguishing feature of GENESIS is its bias toward internal rebalancing before triggering new purchases. Instead of defaulting to additional supplier orders, the system first assesses whether excess stock in one warehouse can cover shortages elsewhere in the network. That shift reflects a broader industry focus on working capital efficiency. According to widely reported industry analyses in recent years, companies have increased scrutiny on inventory turns and cash conversion cycles as interest rates and carrying costs have risen.
By recommending transfers across facilities when feasible, the simulator encourages companies to treat the network as a unified pool of inventory rather than a series of isolated nodes. The result can be lower procurement spend and more disciplined use of existing stock.
The tool also evaluates transportation configurations. It can suggest consolidating shipments to improve truckload utilization or reallocating fulfillment to a different warehouse to reduce lead times. These decisions affect both cost per unit and on-time performance, two metrics that often sit in tension.
“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 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,” said Rodrigo Hermosilla, Research Engineer at the MIT Intelligent Logistics Systems Lab.
From Simulation to Broader Network Intelligence
GENESIS is one of the first outcomes of the collaboration between MIT CTL and Mecalux.
“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 partners have outlined additional research initiatives, including AI-driven internal warehouse replenishment, digital twins for automated storage systems, and slotting optimization. Those areas align with a wider push across the logistics sector to embed simulation and digital twin capabilities into day-to-day planning. Trade reports in recent years have highlighted growing investment in scenario modeling as companies seek to navigate demand volatility, transport constraints, and network complexity.
Simulation Should Shape Capital Discipline, Not Just Inventory Targets
As scenario engines become fast enough for routine planning, they begin to influence decisions that sit beyond replenishment logic. Inventory placement affects working capital exposure, warehouse utilization, and transportation contracts that often run for years. Companies that integrate these simulations into formal budget cycles and network reviews, rather than treating them as isolated planning tools, can tie inventory strategy directly to capital efficiency and service commitments. Recent trade data continues to show how volatile demand and freight markets can strain even well-designed networks; embedding structured scenario analysis into governance processes offers a way to test those pressures before they surface on the balance sheet.