How Johnson & Johnson Uses Shelf-Level Behavioral Analytics To Optimize Planograms

In-store shopper analytics have often been a black hole for brands. Retailer shared data is often constrained to basic store sales. Store traffic data and patterns, customer data, category insights, competitive comparisons and more are often closely held secrets, which makes it difficult for brands to optimize merchandising and marketing in-store.

For example, if you ask most brands “which of their products convert best from the moment a customer picks it up to sales,” they couldn’t tell you. That’s the most critical point of consideration, and yet the data is lacking. They can’t tell you which content best influences shopper behavior by product, or how their packaging lifts sales. It’s more art than science.

Planogram Optimization Using Shopper Marketing Behavioral Analytics

Johnson & Johnson uses Raydiant to engage customers and drive incremental sales in the supermarket segment in Beauty and Over-The-Counter (OTC) products. Using planogram interaction data, Johnson&Johnson can see where customers are picking up products and how they convert to sales. Every single product pickup and put back is automatically understood by Raydiant's industry-leading computer vision, with cameras on the shelf.

Sales Optimization Using Shopper Marketing Behavioral Analytics

That product conversion rate can be used to calculate the revenue per pickup or profit per pickup to look at planogram optimization. For example, in the planogram above, we saw that J&J’s highest revenue per pickup product, Neutrogena Toilettes, were on the bottom shelf, where interactions were lowest. By moving them up among other planogram changes, we substantially increased sales.

We also saw shifts in purchase behaviors from smaller quantity SKUs to larger quantity SKUs, showing the effects on the content we were delivering at the shelf. This informed future content updates that also allowed us to push higher quantity items and increase revenue per trip.

We are also able to compensate for planogram weaknesses by highlighting products in digital content as necessary. All of these optimizations were powered by the data on how shoppers interact with products at the shelf, and how they convert to sales.

Could you imagine marketing online if you couldn’t track conversion? Of course not. Why settle for that in store? If you had data on pickup-to-sales conversion for every product on the shelf, across different configurations, how much could you increase engagement and sales? With the latest shopper marketing analytics, now you can find out.

Book a Demo with Raydiant to learn more!