Demystifying the Four Types of Analytics
Data analytics is often described in terms of 4 broad categories:
➡ DESCRIPTIVE: What happened?
➡ DIAGNOSTIC: Why did it happen?
➡ PREDICTIVE: What will happen next?
➡ PRESCRIPTIVE: What’s the best course of action?
One of the most common misconceptions is that these fall on a linear value scale, implying that the goal is to “evolve” from one category to the next.
In reality, that’s not how it works.
That’s like saying once you learn calculus, you’ll never need algebra.
The truth is that these are often used in tandem; each plays an important and valuable role when applied at the right time, in the right context.
Let’s walk through an example to make this a bit more tangible…
Imagine that you’re visiting the doctor for an annual health check. In a purely descriptive world, your Doctor might say something like:
“Your cholesterol is 215”
Then walk out of the room.
That would be pretty unsettling, because that number is essentially meaningless without additional context.
Are you supposed to be happy or concerned? Has it gotten better or worse Is there something you should do as a result of this news?
Clearly you’re left with more questions than answers…
Next, let’s re-frame this as a diagnostic statement:
“Your cholesterol level is 215. This is on the high end and is likely due to lack of exercise and too much saturated fat in your diet”
We’ve moved from raw data to meaningful information by adding context, and now have a clearer sense of what’s going on and why.
Let’s keep going and take a look at a predictive statement:
“If you maintain your current diet and lifestyle, your cholesterol level will continue to rise, and increase your risk of cardiovascular disease”
Now we not only understand what happened and why, but we also have a pretty good sense of what will likely happen in the future unless we course correct.
Finally, here is a prescriptive statement which is really what you would hope to hear from your Doctor:
“Based on your test results, I’ve prescribed statins and recommended a new diet to lower your cholesterol and reduce your risk of heart disease”
In this particular context, ALL of the information is helpful.
Unless you also happen to be a doctor, you’re completely reliant on having a trained medical professional diagnose the issue, share a prognosis, and prescribe the best treatment for you.
Hopefully this helps demystify what these categories are all about.
If you want to go deeper, check out our brand new course at Maven Analytics: Data Literacy Foundations.
We’ve made it free through March 31st, so you can take the full course even if you don’t have a Pro subscription.
FREE COURSE: Data Literacy Foundations
