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. It also explains how the beloved retailer, Target, used modeling and data analytics to identify women as being pregnant before those same women tell their closest friends and family members.
In this case, the brand used data analytics to predict pregnancies to determine purchasing habits of those who were expecting.
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.
How Brands Uncover Your Data
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).
More recently, Facebook got into trouble for data they were sharing with third parties in the Cambridge Analytica scandal.
This information can be found through:
- Credit cards
- Loyalty card numbers
Through the use of data analytics tools, companies can delve deep into consumer behavior and shopping patterns.
Consumer behavior and understanding why customers buy are critical to the success of any large (or small) retailer.
Nearly every website you access either gathers cookies on you or asks to gather cookies on you. This information gathered from these website analytics is used for marketing and data to learn more about users.
In fact, 99% of cookies on the Internet are used for web tracking and for the purpose of showing targeted ads to users.
💡The Key Takeaway: National and global retailers are spending lots of time analyzing your data to determine how to sell you even more. In fact, they often leverage data points to sell to you without even you knowing it.
The Background Behind Target's Predictive Model
A popular example would be Target's statistician, Andrew Pole, using personal identifiable information (PII) to notice women on baby registries buying large quantities of unscented lotion at the beginning of their second trimester.
The data also showed some time in the first 20 weeks women purchased large amounts of calcium, magnesium, and zinc.
Using these types of data analytics to understand shopping behavior, 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 information obtained can also be used to create psychological strategies to influence consumer spending.
💡The Key Takeaway: Pole was able to see the shopping trends of pregnant women by analyzing consumer data. Through this, he could then make a reliable prediction.
Target Garners National Attention
Believe it or not, data analytics in business can sometimes lead to confrontation, as you’ll read below.
The story that garnered national attention began with an irritated father entering a Target in Minneapolis.
He began talking to the store manager, complaining about Target sending his daughter a sale booklet for baby clothes, cribs, and diapers even though she was still in high school.
Shocked and surprised, the store manager apologized to the angry father.
Yet, the same store manager 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.
💡 The Key Takeaway: As Target used data analytics to predict pregnancies, they received a bit of negative attention. The story above not only proves how accurate data can be, but the impact it has on consumers.
Dialing Back the Creep Factor
Over time, the Target advertising team learned to find out consumers get really freaked out if the store knows them too well, especially with intimate details like pregnancy.
The marketing department understood they needed to mix these targeted advertisements 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 allow for proper targeting but it's not as direct and does not seem as invasive.
Understanding how to incorporate the information obtained from data analytics tools is just as important as the findings uncovered.
This story is a quick example of how data analytics and product segmentation are 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."
💡 The Key Takeaway: When Target used data analytics to predict pregnancies, they had to avoid coming off as invasive. In order to do so, the store carefully incorporated targeted advertisements with the help of a savvy marketing team.
Our Take on Predictive Analytics
As we covered earlier, data analytics tools are often used to help predict the feasibility of a brand’s new service, product, or campaign.
They can deliver detailed information about a customer base or predict the ROI of a specific campaign.
But getting back to the basics–what are the best ways to ensure the outcome of that feasibility study?
Below, we’ll list a couple out a couple of tips for collecting predictive analytics.
Tip #1: Plan for tomorrow by creating clear goals today
Why should you start planning ahead when it comes to predictive analytics?
The same reason you would for any other project: understanding all the factors that will come into play.
It’s a good idea to have an end goal or core objective in mind before you even dive into the data.
Tip #2: Create an algorithmic outline
To have a good grip on how an algorithm works, a proper outline of said algorithm needs to be in place.
Gather the key points or main objectives and then go from there. This will not only simplify the process but also allow the best results to come through.
Tip #3: Know the limits
While a predictive model can’t foresee everything that will happen, it gives a general idea of the data you’ll receive.
That being said, keep in mind that it won’t be able to target major market shifts or other similar changes.
Tip #4: Be realistic about the process
Lastly, understand that while predictive analytics techniques can be immensely useful, they aren’t everything.
The main point is to gather the data and then make informed decisions based on that data.
We find that these tips are a good foundation for the key components of a market research feasibility study.
💡 The Key Takeaway: Predictive data is incredibly important, but it’s also important for expectations to be realistic. Whether it’s Target or a small business, predictive data can have a massive impact on a brand.
Drive Research is a market research firm in Syracuse, NY that uses predictive analytics to test the feasibility of the success of campaigns, new products, and new services. Our team works with brands across the country to analyze customer databases and create custom studies to gather data to make decisions.
Questions about how we can help? Contact us today.
- Message us on our website
- Email us at [email protected]
- Call us at 888-725-DATA
- Text us at 315-303-2040
George is the Owner & President of Drive Research. He has consulted for hundreds of regional, national, and global organizations over the past 15 years. He is a CX-certified VoC professional with a focus on innovation and new product management.
Learn more about George, here.