Find A-Ha's in Your Data!

The headline: Sometimes the 'a-ha moments' we're searching for in our data are hidden in plain sight. Other times, we need to just keep putting in the work until we find them.

Why it matters: Most 'data people' share one thing in common -- we love 'a-ha moments' in data. We love discovering a hidden pattern, diagnosing a root cause, or providing a simple explanation to a complex issue. But it doesn't happen every day.

The backstory: I find a lot of trash running on the side of the road. I've learned there's a high correlation between people who drink those 50 ml mini-liquor bottles (while driving apparently) and people who litter. It's actually quite astonishing.

I found a $5 bill last year. It sparked something in me. Since then, I've kept my eye out hoping for bigger payday. The thrill of the hunt is real. I would see a promising green paper a few yards ahead, only to be disappointed when it was trash.

But no luck. I ran countless miles without finding anything interesting... until May 26th.

I was on mile 5 of a long run. I was lost in my thoughts running on the side of two-lane Andersonville Road when I saw a small sunglass bag. Inside was a seemingly brand new pair of Oakley Holbrook Jade Iridium sunglasses. A-ha! It was a miracle!

Before you judge. It was a busy road and a thunderstorm was approaching. They were precariously less then a foot away from cars whizzing by. I didn't steal them, I saved them (and will gladly return them if you know the rightful owner).

Back to data: I've had the privilege of helping clients investigate and solve many mysterious issues in their data. And it is a privilege. I enjoy it. The thrill of the hunt is real. Creating the elusive 'a-ha moment' is better than finding a roadside sunglasses.

So what? I wish I could share the stories of my a-ha moments, but have a responsibility to keep them confidential. But, I can share a few tips that help me find them. Here are five tips I've found helpful when searching for the a-ha moment:

1. Consider the source. All data is created through a process. It's critical to understand it well enough to know where it can fail. By they way, if there's a human involved, it likely will.
2. Ask dumb questions. I don't take anything for granted. When conducting a data investigation I'm not afraid to ask questions others may expect I should know. It prevents assumptions.
3. Look for the micropatterns. If the issue was obvious, it wouldn't require a 'data nerd' to solve it. Look for small trends by slicing measures across multiple dimensions.
4. Don't ignore the obvious. Sometimes the issue is staring you in the face. Sometimes there isn't more to the story. Sometimes the right answer isn't an a-ha moment.
5. Take a break. This is number one. Running is more of a mental and spiritual activity than a physical activity for me. It helps me think. When you're stuck, step away.

Final thought: I love data, but I especially enjoy finding patterns in data that provide insight and meaning to a story that can help us solve problems. Feel stuck searching for your a-ha moment? Message me -- I would genuinely enjoy to be a sounding board.

This article is part of my blog, Running Thoughts on Data. My first post, The Story My Data Cannot Tell, shares the genesis of my blog. The views and postings on this site are my own and do not necessarily represent those of Plante Moran.