Return to page

Assortment Optimization

Stocking the Right Products to Meet Demand with AI


Traditionally retailers have stocked their stores with the same products based on the season or featuring the current product lineup with only limited variations. Different store locations, however, have different customers, different weather, different display capacity and inventory capacity resulting in very different needs. The result of one-size approach is “stock outs” on hot items and markdowns on others, both costing the retailer hard-won profits. Customer satisfaction and loyalty are also greatly impacted when shoppers cannot find items in the store that they came to see and buy.


AI is ideal for optimizing assortment for retailers. AI models can look at a variety of factors including past sales, store display space, local trends, online behavior, predicted weather patterns, and more to determine which products would be the best fit for a given store location. This AI based optimization prevents stockouts by sending more inventory to stores where products are most needed and minimizes markdowns by making sure that products are on display where they can be sold at full price. AI models can even reroute inventory between stores to ensure that retailers can take advantage of local trends.


The mission at is to democratize AI for all so that more people across industries can use the power of AI to solve business and social challenges. Leading retail brands like Macy’s, Walgreens, eBay and HEB and more use technology to forecast product demand, create personalized customer experiences, and drive advanced inventory planning. H2O Driverless AI is an award-winning platform for automatic machine learning that empowers data science teams to scale machine learning efforts by dramatically increasing the speed to develop highly accurate predictive models. Driverless AI includes innovative features of particular interest to retail brands including machine learning interpretability (MLI), reason codes for individual predictions, and automatic time series modeling.

Related Case Studies

Daqing Zhao
Director, Advanced Analytics, Macy's

"With H2O we are able to build models quickly so we can find patterns that we can use right away"

Satya Satyamoorthy
Director of Software Development, Nielsen Catalina Solutions

"H2O allowed us to interface directly with our existing application and it scales for our massive data set. There is nothing else like it."