In this clip from our webinar, Turning AI into Results: Practical Applications Across Supply Chain Planning, Zac Nemitz from John Galt Solutions explores the benefits of AI in supply chain planning, in particular Multi-Echelon Inventory Optimization (MEIO).
Zac explains how traditional inventory approaches often focus on optimizing individual locations in isolation, which can lead to inefficiencies across the broader network. MEIO changes that by enabling organizations to optimize inventory holistically, considering the full flow of goods from suppliers through to customers.
By combining MEIO with AI and machine learning, companies can account for a wide range of real-world variables such as transfer rules, lead times, shelf-life constraints, and varying inventory targets. This results in a more balanced approach that reduces shortages, controls storage costs, and minimizes transportation spend.
The Atlas Planning Platform helps teams go beyond inventory optimization and apply MEIO for comprehensive control and visibility. With a complete, end-to-end view of the network, teams can better understand how decisions impact the entire system and confidently evaluate multiple scenarios.
Key Highlights of AI-driven MEIO:
- Holistic network optimization instead of siloed decision-making
- AI-powered modeling that incorporates complex, real-world constraints
- Improved visibility for scenario planning and cross-team alignment
Watch the webinar to learn more and explore how Atlas can help you unlock AI to improve inventory planning and other key areas of supply chain to deliver real value: Turning AI into Results: Practical Applications Across Supply Chain Planning
- Full Transcript
Zac Nemitz: MEIO is Multi-Echelon Inventory Optimization. If you think about your current network, if you were operating, in a non-MEIO and more just a standard inventory optimization operating model, you would try to optimize for each storage location individually.
MEIO is great because it lets me look at my entire network, anything that I have related to inputs and outputs of inventory, and I'm able to optimize across all of those locations. You know, the benefit of leveraging AI and machine learning techniques behind the scene of this is we're able to optimize for a wide variety of variables, so if you think about your network, do you have transfer rules? Do you have varying lead times from suppliers and in-network? Do you have FIFO or FIFO rules if there's sanitation considerations and expiration of sanitation? Maybe you have expiration of just shelf life products. What inventory targets do you have? Do those inventory targets vary by product type or customer?
All those things are considered and leveraged within the Atlas MEIO model to help us reduce, you know, shortage costs and manage storage costs within thresholds, and then, obviously, you also want to optimize for the amount of transportation costs that you're spending moving stuff around.
This other benefit I've seen a lot is just the ability with MEIO to provide a holistic view. So, I'm not looking at little silos of my network. I'm able to see the whole picture, and kind of the ins and outs of the whole picture, and how these things, react to each other. And that feeds into a lot what we've talked about from, like, a scenario implications, scenario management, and scenario capabilities, so I can understand given a scenario, what does that mean for my network inventory plan? What does that mean? Am I able to support these types of things?
There’s a lot of value to be had there beyond just the actual math and the outputs, but also just clarity and visibility across the organization for any sort of scenario and alignment discussions.
