Luxury Department Store
- RETAIL SEGMENT: Luxury Specialty Department Store / Luxury Apparel Outlet
- PRODUCT: Discover
- OPPORTUNITY: Increase conversion on the category page
- SOLUTION: Personalize the sort order of products displayed on category and sub-category pages
- RESULTS: 2 – 5% increase in website revenue as compared to nonpersonalized category page
Opportunity: Increase conversion on the category page
On average, 33% of online shoppers visit a category or sub-category page when they visit a retailer’s online store.1 Currently, almost all retailers sort their category product results the same way for each and every visitor. Whether it’s a shopper’s first visit or the 100th return visit of a loyal customer, the category product results displayed are sorted exactly the same. While the in-store merchandiser’s goal is to appeal to as many as possible, online shopping has the potential to be an individualized experience. Retailers have the opportunity both to curate a personalized experience for a recognized customer to find a product quickly as well as to increase shopper engagement. This engagement drives loyalty, which in turn drives increased sales—and allows the retailer to provide better customer service by improving personalization across all their channels and touch-points.
Solution: Personalize the sort order of products
Discover™ is a real-time retail application that brings the most relevant items for an individual customer to the top of the list—helping shoppers quickly find the products they seek. With Discover, product lists on the category and subcategory pages are pre-sorted on page load to best match each customer’s historical and current shopper behavior.
For a recognized shopper, the personalization algorithm analyzes the individual’s historical views, clicks, purchases, and searches (based on inputs such as categories, products, and brands) to personalize the order in which available products are presented. If this recognized shopper looked at specific products or brands on the retailer’s website in the current session as well as in past sessions before visiting the category page, the algorithm takes into account this real-time behavior as it generates the product listing that’s the best match. For an unrecognized shopper, products are sorted based on a combination of global attributes such as top viewed, clicked, and purchased items in that category.
Both the attributes and their associated weightings can be configured to a retailer’s specific needs, and then automatically optimized using machine learning and multivariate testing. For example, if brand is critical to the retailer’s customers, brand can be added as an attribute, and weighted more heavily than other personalization attributes. Examples of personalization attributes include products, categories, and brands the shopper has viewed, clicked, and purchased in the past and/or during the current visit.
Results across diverse businesses: 2 – 5% increase in website revenue
Discover was launched on a luxury apparel retailer’s website and delivered a consistent 2 to 5% overall increase in website revenue. It receives C-suite visibility and its continued strong performance has since shifted the retailer’s business strategy and prioritization; they have accelerated its deployment to their other online retail stores.
Discover was also launched on the retailer’s outlet and exceeded performance expectations with a 5%+ average increase in website revenue. Within a couple of weeks, the retailer had 100% of the outlet site traffic enabled for Discover.
Presenting shoppers with a concise listing of the right products quickly is paramount. How long it takes shoppers to see relevant recommendations can mean the difference between conversion and an abandoned cart.
What is the most expedient way to help shoppers find what they seek? By satisfying the customer’s agenda through algorithm-driven personalization. The outcome is dynamically generated, personalized product lists—clearly relevant to that specific individual—built on a customer’s past and current shopping behaviors.
[normal-button color=”highlight” url=”/wp-content/uploads/2017/04/Discover_Case_Study.pdf” label=”DOWNLOAD” blank=”0″]