We employ clustering algorithms to group customers based on their purchase history, product preferences, and other relevant factors. It allows us to create personalized product assortments for each customer segment.
We allocate our products and budget to each store based on the historical preferences of each customer segment for product attributes.
By analyzing customer segments and identifying their needs and preferences, we were able to bridge the gap between merchandising and customers.
Our persona-driven assortment approach has the potential to increase full-price sales by up to 12%.