At BikeSomeWhere.com, CEO Jeff Stone figured there must be a better route to serving up personalized content to his customers. So he turned to two technology vendors, one that specializes in product recommendations and the other in site search, and asked them to work together to give his customers a shopping experience more suited to their interests.
BikeSomeWhere`s site search vendor, SLI Systems Inc., was already working on prioritizing within search results the best sellers among, say, the 400 pairs of biking gloves the retailer sells. But after SLI went to work with Certona Corp., the personalization vendor, BikeSomeWhere was able to further prioritize among those 400 biking gloves the brands and complementary products the shopper had shown the most interest in previously.
After several months of integrating applications and working out business rules, BikeSomeWhere offers more personalized search and navigation that Stone says has increased the percentages of shoppers clicking into product displays and converting into buyers. "With more personalized search results, our customers didn`t have to keep searching deeper into site search results, and we definitely saw an increase in conversions," he says.
The BikeSomeWhere example illustrates how personalization systems increasingly are being integrated with other e-commerce systems to engage shoppers and move e-retail closer to achieving one of its early promises—that of providing each web shopper with an experience tailored to her preferences.
At Tobi.com that takes the form of merging recommendations technology with the cameras built into many personal computers to allow a shopper to see what she would look like wearing items likely to interest her.
Tobi in November became the first online retailer to deploy Fashionista, an application developed by technology partners Zugara, which provides the interactive video and computer-generated content, and RichRelevance Inc., which supplies the product recommendation engine.
When a shopper clicks on the Fashionista application on Tobi.com, a live webcam image of her standing in front of her computer appears within a window alongside images of several pieces of apparel she might like. The recommendations that initially appear are based on the shopper`s known shopping behavior as recorded by RichRelevance web analytics.
To try on a dress, the shopper moves her hand to make it appear near that dress on the computer screen; the augmented reality technology within the application then makes the dress appear in front of the shopper`s image as if she were wearing it.
If she likes the dress, the shopper moves her on-screen arm near a thumbs-up illustration, which sends the image of the dress into a virtual closet and increases the relevancy score of the recommendation; if she doesn`t like the dress, she moves her arm near a thumbs-down illustration that removes the dress from her recommended items list.
Items placed in the virtual closet can be reviewed at any time and, with a mouse click, placed into a shopping cart for purchasing. Fashionista also lets the shopper save a still picture of herself appearing with an overlaid garment she likes and to send that image to her Facebook page to elicit comments from friends.
Each thumbs up or thumbs down not only teaches the system more about what that shopper likes, it also improves the recommendations shown to other shoppers with similar traits.
Jeff Lee, vice president of products and technology at Tobi, says Fashionista helps make shopping the e-commerce site both personalized and fun, much like what consumers expect from visiting fashion boutique stores.
"Fashionista not only helps answer the question, `How does this look on me?` but it also provides for a more fun and engaging way to shop and discover products online," he says. "This helps shoppers find new products on our site they might not find otherwise."
Although Tobi for now is making the Fashionista tool available only for dresses, positive feedback from customers has Tobi considering it for other women`s as well as men`s apparel categories, Lee says.
Zugara and RichRelevance have not said publicly what they`re charging for Fashionista. But David Sellinger, CEO of RichRelevance and a former head of personalization technology research and development at Amazon.com Inc., says Fashionista is designed with a flexible pricing model based on pay for performance.
Retailers are also using personalization technology in connection with other applications to grow in new product categories.
Coastal Contacts, an online retailer whose primary product, contact lenses, is not much helped by personalization systems, is turning to customized web content to spur its growth in the more fashion-oriented categories of sunglasses and prescription eyeglass frames, says Braden Hoeppner, director of web sales.
Coastal Contacts is personalizing its web page content with Unica Corp.`s Interactive Marketing OnDemand application, which combines web analytics, site personalization technology and e-mail marketing capabilities.
"We see where a shopper came from, whether they`ve been on our site before and how far they got in the purchase cycle, and we personalize pages by prioritizing products the shoppers have looked at before," Hoeppner says.
With more than 10 years of experience in working with web analytics to drive marketing and merchandising efforts, Hoeppner adds that the personalization technology he uses today is far simpler to set up and use than what he has worked with in the past.
Those personalized promotions might be related to a particular style of eyeglass frames that a shopper has observed in past site visits, or to what`s happening at the moment where the consumer lives. "If I know that shoppers in New York are dealing with a major snowstorm, I may show site visitors from New York special promotions to take advantage of the fact that people there are shopping online more to avoid the snow," he says.