Oracle Retail Blog helps retailers stay current on customer successes, hot retail trends and industry best practices.

University Collaboration on Tapping Into the Power of Endcap Displays

Troy Parent
Senior Director, Retail Science & Insights

The number of displays in any store is limited, therefore decisions regarding which products to place in these high-value locations need to be strategic and produce the highest revenue or profit lift. While a typical large grocery retail store may have anywhere from 60,000 to 300,000 SKUs, on average, it will have just 36 endcaps. With this in mind, Oracle Retail data scientists teamed up with Moore School to help retailers optimize product placement in these critical positions, which give products a 93% increase in exposure. See more in Spirited Magazine.

Moore School management professors Mark Ferguson and Olga Perdikaki collaborated with Su-Ming Wu, a senior principal data scientist at Oracle Retail, to research estimation and optimization models that retailers can use to indicate which product has the best chance of being purchased from an end-of-aisle display to optimize store profit. 

The project had two objectives: 

  1. Help retailers estimate the revenue lift for specific categories, subcategories and/or SKUs
  2. Optimize store revenue and profit by picking the right products for displays   

The team decided to focus on using beer as the primary product for display placement in this research study. They determined which beer had the best chance of being selected from a display rack, and which particular beer was the best to display for a given week. 

"The model can give a grocer or other retailers a whole year’s plan and can be used with any product category," Ferguson said.

The research insights include:

  • A hierarchical technique for choosing the best product, among the vast number of SKUs at a typical grocery store, for maximum revenue and profit margin
  • Techniques for calculating and predicting profit and revenue lift
  • A specific example of optimization results from applying these techniques to historical beer sales data collected by IRI

The Moore School team “basically developed the math behind it,” Ferguson said. Continue reading the article from Darla Moore School of Business

Download the Research - Grocer Guidebook: Predict Sales Lift with Advanced Stats

Grocer Guidebook: A Collaboration with USC and Oracle Retail Science Researchers







Be the first to comment

Comments ( 0 )
Please enter your name.Please provide a valid email address.Please enter a comment.CAPTCHA challenge response provided was incorrect. Please try again.