Kashmir Hill, from Forbes, reports in How Target Figures Out a Teen Girl Was Pregnant Before Her Father Did that Target is data-mining purchases to predict who is the early stage of pregnancy.
By cross-referencing a lot of purchasing data, Target can calculate the probability of a customer being pregnant and even estimate a delivery date. The article quotes Charles Duhigg of the New York Times:
[The Target statistical analyst] was able to identify about 25 products that, when analyzed together, allowed him to assign each shopper a “pregnancy prediction” score. More important, he could also estimate her due date to within a small window, so Target could send coupons timed to very specific stages of her pregnancy.
How is this done?
The Forbes article says:
Target assigns every customer a Guest ID number, tied to their credit card, name, or email address that becomes a bucket that stores a history of everything they’ve bought and any demographic information Target has collected from them or bought from other sources.
Using that treasure trove of information allows Target to do an incredible amount of analysis.
Then coupons for baby stuff can start going out to the customers. Perhaps before the joyful news has been announced! See the article for an actual incident, which drives the title of the article.
Think about the ability to figure out all sorts of things. Hmmm. Who just bought a new house, just got a huge raise, or got laid off? How about who just moved in together, who separated, or who’s having an affair?
Don’t get mad at Target. I’ll bet that every retailer, on-line and off-line, is doing the same thing.
(hat tip: Saundra S.)
One thought on “Predicting who is expecting by their shopping patterns in the second trimester – the power of data-mining”