HOW ABERCROMBIE USES AI TO TAKE THE ANGST OUT OF INVENTORY PLANNING

Molly Kozar, senior director, omni location planning, Abercrombie & Fitch Co., discusses fusing ‘gut instinct’ and AI data to optimize inventory.​

retail rx caught up with Molly Kozar, senior director, omni location planning, Abercrombie & Fitch Co., on how the company has reaped the benefits of AI. The retailer has been using Syrup Tech’s AI platform to optimize inventory for about a year now.

“AI is helping our teams be more precise on how we deploy inventory across the globe,” said Kozar. “Within the last few years, really, Abercrombie has been experiencing change—brand positioning, target customer, store footprints, the mix of digital versus physical, it’s all changing. AI is one of the tools that we have been able to leverage to give us that speed and flexibility to keep up.”

Here, Kozar speaks to some of the common questions retailers bring up when it comes to AI.
RETAIL RX: Historical data can prove to be inappropriate for the program or items that are being planned. How do you address the classification of historical data to allow the AI models to improve predictive accuracy?
molly kozar: Human intelligence can really shine by being able to adjust the AI models. Planners still need a strong understanding of what is driving their individual business as well as what is going into the AI model output for this exact scenario. Companies should look at AI as a blend of art and science. Utilizing humans in lockstep with AI is truly where the magic happens. In my experience, tools are never a ‘set and forget.’
RETAIL RX: Can you give an example of how you would leverage AI to help you forecast a new style/store in the marketplace?
M.K.: We opened 60 new experiences last year and expect to continue to be a net store opener again in 2024, and AI is a way that we can further understand those new experiences. It’s critical for those locations to be able to get that information quickly so we’re able to adapt and make sure our customer is getting exactly what they need. AI is a helpful tool to experiment with when looking to identify new trends in the industry. This is beneficial for forecasting new types of products for example, because it gives a variety of potential ideas that might align with what you are trying to visualize or solve for.
RETAIL RX: How do you measure the impact of AI in your supply chain decisions to know that AI is bringing in actual value?​M.K.: First, it is important to understand what metrics are most important to the end result your company is trying to solve. Next is defining baseline metrics and constantly measuring against those, which will allow for a variance between business as usual and some of the AI additions.

RETAIL RX: Has the A&F Co. supply chain, in particular your garment manufacturers, felt the positive impact of A&F Co.'s use of AI to generate more accurate early forecast versus final and actual quantity buys to the factories?
M.K.: When looking at any technology, AI included, we continue to integrate feedback from all areas of the business with the end goal of driving efficiency, accuracy and speed. Involving stakeholders across teams has allowed us to continue to test and learn while bringing perspectives from across the company.​

RETAIL RX: How has AI/Syrup Tech helped A&F predict or plan/allocate something in a way that maybe you wouldn't have before? Beyond using internal data, do you use external data (e.g., social) to localize product placement?

M.K.: My team is focused on continuing to improve the placement of inventory and new ways to experiment with AI. We have seen new examples through our test and learn approach of using additional data sets such as weather, social media engagement, and internal data in combination with historic information for accurate end results. Learning how this has worked in the past and applying it to new use cases in the future will help us continue to evolve. We have seen examples of both internal and external data enabling our teams to continue to stay close to the customer. The goal is to help build the experience that services the customer wherever they choose to interact with us.​