How Target Used Data Analytics to Predict Pregnancies

December 6, 2016

As crazy as that title may seem, the case study is absolutely true. Using big data and predictive analytics can tell a frighteningly accurate story. This Target story may be something you've seen or read over the years online or in Charles Duhigg's book on The Power of Habit but it's worth recapping. It was also featured in the New York Times and passed along to me by a colleague years ago. Either way, the story is pretty fascinating, so I am going to recap it here for you. For some readers new to the data analytics or market research field, this example displays the power of big data and how it is used to profile customers and predict purchase behavior.

 

 

 

Whether you know it or not, you as a shopper are sharing highly detailed buying patterns with retailers as you shop on a daily basis. You unknowingly (or knowingly if you work in this field) provide this data through customer IDs tied to personally identifiable information (PII) such as credit cards, emails, and loyalty card numbers. These national and global retailers are spending lots of time analyzing your data to determine how to sell you even more. A popular example would be Target's statistician Andrew Pole using PII to notice women on baby registries buying large quantities of unscented lotion a the beginning of their second trimester. The data also showed sometime in the first 20 weeks women purchased large amounts of calcium, magnesium, and zinc. Using all of this shopping behavior data, Pole could then assign a pregnancy prediction score to customers based on the purchase and purchase volume of about 25 different products in-store, regardless of baby registries.

 

The story that garnered national attention began with an irritated father entering a Target in Minneapolis talking to the store manager, complaining about the store sending his daughter a sale booklet for baby clothes, cribs, and diapers even though she is still in high school. Shocked and surprised the store manager apologized, yet received a call from the same father weeks later to find out the father had a talk with his daughter and discovered she was indeed pregnant. Target knew this (based on their pregnancy prediction score) before she even told her mother and father.

 

Over time, the Target advertising team learned to find out consumers get really freaked out if the store knows them too well, especially intimate details such as being pregnant. The marketing department understood they needed to mix these targeted advertisements in with others to lessen the "creep factor." So now that same pregnant customer sees ads in their sales booklet for not only diapers and cribs but also other foods, household items, lawn care items, and clothes. The mix and match still allows for proper targeting but it's not as direct.

 

 

This story is a quick example of how data analytics and product segmentation is used to predict behavior. It's not enough to just collect this data from a variety of sources as an analyst. Finding ways to tie databases together and spending the time to fully examine the data to identify trends and commonalities is the key to generating these types of insights. Make sure your company is not only "data heavy" but also "insight heavy."

 

Drive Research is a market research firm in Syracuse, NY who uses predictive analytics and models to test the feasibility of success of campaigns, new products, and new services. Questions about how we can help? Contact us at info@driveresearch.com or by calling 315-303-2040.

Please reload

Featured Posts