• This field is for validation purposes and should be left unchanged.
Guidance and results for the data-rich, yet information-poor.

Avoid Focusing on the Obvious when using Data Analytics

GiraffeGetting too focused on the obvious can lead to big mistakes in the world of data analytics. A recent Gigaom article called these obvious portions of the data “giraffes,” defining them as “portions of data which dominate the rest of the data and hide important insights.”

Giraffes are particularly dangerous when they play into confirmation bias. That was the case in Gigaom’s gaming company case study. The “giraffe” indicated that it was better for these companies to spend more money marketing to men. The gaming company itself likely believed, going into their analysis project, that it was better to market to men, simply because this is a common assumption in the industry. And so, for a time, they missed key insights which indicated that women tend to spend more money as lifetime customers than men do. Rather than solving a key business problem they instead left important insights on the table.

Confirmation bias isn’t the only issue. Sometimes inclusion of factors which are irrelevant to the question at hand will play a role, too. And any time you start diving into data without a clear sense of your objectives you’re all but begging to be misled by some giraffes.

Here are a few additional examples from the article.

  • Understand the effectiveness of your SEO efforts by eliminating all traffic due to searches which include your brand names.
  • Make sure that data on the majority of e-commerce customers–one time purchasers–is not concealing important insights regarding the more valuable–repeat–customers.
  • Make sure that data on the 40% of iGaming customers who churn after the first 24 hours is not leading you to incorrect conclusions about where the most valuable players are acquired.

Discovering if there are any giraffes in your data is sometimes easy–an obviously dominant value will be a huge giraffe eye staring you in the face. In these cases, it’s important not to ignore it. If you don’t see any obvious giraffes at the aggregated level, it’s important to look for one by slicing the data to look for dominant values. The most common way to do this is by adding an additional dimension or two.

In short, I strongly encourage marketers and analysts to dig down into their data, to look out for misleading dominant portions of the data, and not to rely only on high-level, aggregated views.

Learning how to spot these sorts of problems and avoid them is essential before making a large investment in a data analytics project. You count on your data to deliver valuable business intelligence and so need to set it up in a way that does not lead you in the wrong direction.

Learn to spot giraffes and other issues by attending any of TMA’s data analytics training courses. Register today.

Data Mining Webinar

Learn How to Get Predictive Modeling
Off the Ground and Into Orbit
1 Hour Live Interactive Event

Why Train With TMA?

Determine whether TMA training is right for you, and learn why TMA is truly the best option for live classroom analytics training.