Dynamic Personalization Gives SteinerSports.com a 40% Sales Lift

“Location, location, location” is critical when selling real estate. But for Steiner Sports, knowing the physical location of visitors to its e-commerce site helped it increase Web sales by 40% last year.

A seller of sports memorabilia and collectibles, Steiner hit upon the idea of using geographical targeting online after looking at its Web analytics reports and noticing “abysmal” conversion rates from the Boston area, says Alex Schmelkin, president/cofounder of Alexander Interactive, the agency that worked with Steiner on its Website.

The home page of SteinerSports.com often featured merchandise from New York sports teams, particularly the Yankees; as anyone who has ever lived in New York or New England can attest, Bostonians loathe the Yankees and other New York teams with the intensity of a thousand suns. Upon seeing New York memorabilia on the site, many of them fled almost immediately.

So Steiner and Alexander Interactive decided to test using visitors’ IP addresses to determine which teams they were most likely to root for and then serve them landing pages featuring merchandise from those teams. The results were “astounding,” Schmelkin says, resulting in a fivefold increase in revenue compared with nontargeted pages.

Using IP addresses for geographic targeting is a good fit for a company like Steiner, whose merchandise is segmented by locale. But Schmelkin has used it for a fashion retailer as well, tying geographic targeting to weather trends. For instance, when the northeast portion of the country was pummeled by heavy snow this past February, the fashion company served landing pages with “snowed-in specials” to visitors whose IP addresses indicated they were from the areas buried in the white stuff.

Varying page content according to the visitor’s location is just one example of dynamic online personalization, which Schmelkin defines as “picking up on cues that we learn about a visitor to a Website and delivering the experience and products that best meet their needs.”

This sort of personalization can be automated via software that collects visitor data from the Website—the pages visited, the links clicked, the products purchased or abandoned—and, using programmed algorithms, compares the information against other collected data to determine which products or pages the visitor would be most receptive to. “You start giving the software clues with every single click,” Schmelkin says.

Obviously the more data the software gathers from the more visitors, the more accurate the personalization is likely to be. “Generally you need many thousands of impressions of data to start generating valid results,” Schmelkin says. “The real trick is that [the software] picks up on the collective intelligence and makes changes on its own.” All the same, he adds, “we’ve actually implemented [dynamic personalization] for clients where they’ve earned back their ROI with just the first campaign.”

Steiner Sports, for one, uses this type of dynamic personalization to provide site visitors with more-relevant product recommendations and upsells. But as Schmelkin notes, “What we’re doing these days goes beyond just products. It’s product, content, and experience. It’s no longer just that you’ve clicked on TVs and I know you want a flat panel, but that you’ve clicked on TVs and the entire experience is going to show you why you should buy these TVs from us and what you need to know.”