Real-time predictive marketing

[x+1] optimizes clients' sales efforts with SAS^®

Knowing exactly which products and services potential customers need the moment they enter a Web site – before they even log in – is the surest way to optimize your advertising dollars. Using SAS software, [x+1], a leading provider of predictive marketing solutions, knows how to make that happen.

"One of our clients is a major financial services company that offers 30 different credit cards; but as soon as you open its home page, you will only see five of them," says Ted Shergalis, [x+1]'s Founder and General Manager of media+1. "Our job is to build the models that, in real time, know how to implement segmentation results based on various attributes that determine which five cards to show you."

[x+1]'s products leverage traditional and online direct marketing techniques for its clients by anonymously analyzing many types of demographic, transactional and behavioral data. It then uses predictive modeling to automatically determine the right audience for each client and the right offers for each segment of that audience.

The New York-based company accomplishes that lofty goal by using a variety of SAS offerings, including SAS Enterprise Miner and SAS/OR.

How does [x+1] use SAS?
While [x+1] also specializes in helping large companies pick the right Web sites for displaying their ads, it primarily incorporates onsite analytics to help those companies figure out the best way to serve up offers on their own Web sites.

Without SAS to automate the process, the financial services giant Shergalis referenced above would implement campaigns from reports generated from card offer rotations that were determined through business rules.

"Where we come in is we build real-time automated models and score them in real time to provide lifts over business rules by using segmentation techniques," Shergalis explains. "Before SAS, we were using Java script and were only dealing with a limited amount of attributes that were relatively constant across all clients. Before that, we had someone writing a decision-tree program that essentially automated the process.

"But given some of the idiosyncrasies in the data, it really didn't provide as much lift as would be expected. So SAS came along and allowed us to find more patterns within the data and to find more opportunity in terms of generating lift."

What's the value of using SAS?
Using a random control group, [x+1] has determined that its work with SAS has provided the major financial services company a 120 percent lift within the control group and a 30 percent lift based on that company's established business rules.

And, according to Shergalis, [x+1] would need at least four more employees to accomplish the same work without SAS. "And then you have to coordinate among all those people who would have different skill sets, which, from a management perspective, would cause headaches," Shergalis says. "So we wouldn't have fast-paced development, and we probably wouldn't be as innovative. And on top of that, it would take much longer."

SAS allows [x+1] to build a front-end graphical user interface through which employees can build models on the fly. Then, by simply pushing an execute button, the user invokes SAS and the cleansing and transformation process begins. The cleansed data then flows into a SAS Enterprise Miner decision tree, which creates a vast array of reporting functions. Finally, the data goes into a non-linear programming procedure that applies operations research techniques to generate solutions to complicated business rules, such as making sure that a potential customer doesn't get shown the same product offer twice (Proc NLP in SAS/OR).

"The reaction to SAS at our company has been fantastic," Shergalis says. "People are excited to learn about it, because they see how much more productive they can be using it. And when I show the results to my peers on the executive team, I always get the funding I need for further investment in the products and features of SAS because they can see the successes we've had using it."

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.

Copyright © SAS Institute Inc. All Rights Reserved.