Tamara Gruzbarg, senior director of customer analytics and research at private sale site Gilt Groupe, classifies the company’s data analytics environment as “disparate” prior to February 2010. She says the company’s various data sources were located in “different places and formats” and that “no single tool could access all of them.”
“We had issues with the simplest reports,” she says, “because critical information was located in different places. We needed a strong tool to access and manipulate data.”
Gilt Groupe turned to SAS, the Cary, N.C.-based business analytics technology and services provider, to bring all of the company’s data sources under one all-encompassing silo. Within a short period of time, Gilt Groupe was able to “marry transactional information with online behavior,” says Gruzbarg. “As we got more sophisticated, we were able to understand purchase behavior and we created very predictive models based on this information.”
With the help of SAS Analytics Pro, Gilt Groupe was able to determine an individual member’s average time on site, purchase frequency, most-viewed products, and when the consumer abandons shopping. “You can see what peaked or decreased user interest,” says Gruzbarg. Another critical improvement, she says, was using behavioral information to deliver relevant products to individual customers.
“If we have 50 sales a day, we can’t fit all 50 in one email,” she explains. “With SAS, we can figure out the top sales to put in front of you based on your preferences.”
Gilt also discovered that as it grew from a women’s apparel site into a site that offered various product categories, it could better market to what Gruzbarg calls, “cross-shoppers.”
“People might learn about Gilt as a women’s shopping website,” she explains. “But if someone came in as a women’s shopper we had to get them to think about all categories…We tried to look at the entire women’s base and figure out if we had women to whom we could make a compelling offer to prompt them to shop on the men’s site.”
Gilt built a model and implemented a series of campaigns to encourage women to cross-shop on the site. Based on this modeling, 100% of the targeted women eventually made purchases on the men’s site.
In addition to cross-shopping, the company witnessed a 10-20% lift for customers browsing in new merchandise categories who had not purchased in those categories (percentages vary depending on the category). It also saw a 20% increase in new member conversion rates.
Although Gruzbarg was satisfied with the first year’s results, she said she would like to see the SAS product operate closer to real-time. “With SAS, the way we operate the actual prediction and analytical work is not real-time, but the models are built in a traditional time frame. A week’s time frame is not a minute’s time frame.”
In response to Gruzbarg’s assessment, Jonathan Hornby, director of marketing at SAS offered the following: “Gilt Groupe is using SAS Analytics Pro, which while a very versatile and powerful analytical tool was not designed to provide real-time functionality,” he said. He recommends customers in need of real-time analytics implement SAS Real-Time Decision Manager “to deploy analytic models in real-time environments spanning online, social and call center.”