New York Times Story Sheds Light on Predictive Analytics

A recent story from the New York Times about habit patterns and predictive analytics begins with an irresistible hook:

“Andrew Pole had just started working as a statistician for Target in 2002, when two colleagues from the marketing department stopped by his desk to ask an odd question: ‘If we wanted to figure out if a customer is pregnant, even if she didn’t want us to know, can you do that? ‘”

The article, taken from a section of author Charles Duhigg’s upcoming book, The Power of Habit: Why We Do What We Do in Life and Business, moves back and forth between a “Target-knows-you’re-pregrant-without-you-telling-them” story and background information on the author’s research into habit cycles and how they influence our thought processes and behaviors. (Note: if you’re only interested in the section of the story that focuses on Target’s use of predictive analytics, this article from Forbes sums it up nicely.)

Basically, Target, like most major retailers, assigns some type of unique ID to each shopper, and then every recordable interaction that the shopper has with Target (purchases, coupon use, survey participation, refund requests, contact with customer service, etc.) is associated with that shopper’s unique ID. Of course, also linked to this ID is any demographic information that Target can acquire: age, ethnicity, marital status, number of kids, address, job history, distance from the nearest store, estimated salary, Web sites visited, reading habits, brand preferences, and even political persuasion. Then, once this information is acquired, it’s the job of statisticians like Pole to analyze it and make it useful.

As the article goes on to explain, Pole and other Target number crunchers determined a few ways to increase their chances of predicting that a shopper is pregnant. Apparently, expecting mothers begin buying larger quantities of unscented lotions as well as supplements like calcium, magnesium, and zinc. And when these shoppers begin buying more scent-free soaps, cotton balls, sanitizers, and washcloths, it’s a good bet that they’re getting closer to their due date.

Not unexpectedly, retailers capitalize on these types of data-enabled predictive analyses by customizing the offers and marketing material that shoppers receive. In the case of Target, this led to a incident that forms one of the most captivating parts of the article: a Minneapolis father recently lodged an angry complaint to his local Target manager when his teenage daughter began receiving coupons from the retailer for baby clothes and cribs—only to have to apologize to the manager days later when his daughter finally told him she was pregnant. Or, as it was tantalizingly summarized in a number of links when the article first spread online, “Target knows you’re daughter is pregnant before you do.”

Major retailers understand, of course, that people are becoming more and more concerned about the amount of information that companies know about them. The article quotes an unamed Target executive on their solution to this problem:

“[W]e started mixing in all these ads for things we knew pregnant women would never buy, so the baby ads looked random. We’d put an ad for a lawn mower next to diapers. We’d put a coupon for wineglasses next to infant clothes. That way, it looked like all the products were chosen by chance.

And we found out that as long as a pregnant woman thinks she hasn’t been spied on, she’ll use the coupons. She just assumes that everyone else on her block got the same mailer for diapers and cribs. As long as we don’t spook her, it works”

So, at a time of growing concern about privacy and the amount of data collected about customers, it appears that retailers like Target have started taking more subtle approaches to exploiting their knowledge about the details of peoples’ lives. Rest assured, though, they're still keeping track.

Have you ever considered

Have you ever considered creating an ebook or guest authoring on other sites? I have a blog centered on the same topics you discuss and would love to have you share some stories/information. I know my visitors would value your work. If you're even remotely interested, feel free to send me an email. Wm Bouffard

Post new comment

The content of this field is kept private and will not be shown publicly.
By submitting this form, you accept the Mollom privacy policy.