Fewer coupons, more sales

Belgium grocer Colruyt uses predictive analytics to tailor promotions, boost customer spending

What if every household received promotional coupons that closely matched what it actually wanted to buy? That was Belgium grocer Colruyt’s goal. Using predictive analytics, the company is sending fewer coupons, while increasing household spending.

A larger percent of households now use our promotional coupons, and the increase resulted in a larger average spent in our stores by cardholders. Equally important, it indicates a clear increase in customer loyalty.

Bart Van Roost
Department Head of Strategic Marketing and BI

The Colruyt Group operates 217 stores. It sends its 1.6 million loyalty cardholders promotional coupons every other week. But Belgian mailboxes are stuffed with promotions from other retailers. “This makes it difficult to grab their attention and reach customers with our message,” says Bart Van Roost, Department Head of Strategic Marketing and BI. “We began searching for a way to make sure that customers look at our leaflet."

"If customers go through a folder only to find out that there are no products of interest, they feel we have wasted their time,” he explains. The concern: Customers won’t bother to open future promotional envelopes. While segmenting customers is a partial answer to this problem, Colruyt wanted to go beyond that. “What we had in mind was nothing less than selective marketing – marketing on an individual basis.”

But how do you customize the coupon selection for 1.6 million cardholding customers? Especially considering the stores carry 11,000 products and put 400 of them on promotion every other week. “We obviously required a powerful application with advanced analytical capabilities,” Van Roost says. After conducting two proof-of-concept trials, the company chose SAS to give it the capabilities needed to be that “customer-ready business.”

Calculating purchasing probabilities

With SAS® Enterprise Miner™, Colruyt is able to calculate purchasing probabilities based on past customer behavior, as well as on household and demographic information stored in its database. Of the 400 products on promotion during a given two-week period, each household receives four pages of coupons specifically tailored to it, down from 32 pages previously.

Van Roost says that speed is critical to the program’s success, as is the ease in setting up rules so, for instance, households don’t receive more than eight promotions within the same product category.

Fewer promotional coupons, higher return

Along with higher per-household spending, the retailer is saving a lot of money on paper. “We’ve saved 665 million pages of paper a year, as well as the associated printing and mailing costs,” Van Roost says. “A larger percent of households now use our promotional coupons, and the increase resulted in a larger average spent in our stores by cardholders. Equally important, it indicates a clear increase in customer loyalty.”



Increase promotion effectiveness with customized offers.


SAS® Enterprise Miner™


  • More cost-effective marketing: Households only receive promotions related to products they are interested in, thereby stimulating more coupon use.
  • Increased spending per capita: The average amount spent in store rises for customers using these coupons.
  • Significant cost savings: This new marketing approach saves 665 million pages of paper a year.
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.