The DataHero Blog

Drag-and-Drop Cohort Analysis

October 25th, 2013

Introducing Cohort Analysis

Cohort analysis is a powerful technique for understanding how groups of users behave over time. How does the behavior of users who registered this month differ from those who registered last month? Are open rates for email marketing campaigns impacted by when a person signed up? And so on.

Unfortunately, cohort analysis is really hard to do.  In Excel, you need to build complex pivot tables and do lots of manual calculations (this 7-minute video shows how to set up a single cohort in Excel).  Tableau requires you to construct “Calculated Fields” and construct formulas to define each cohort.  Of course, you could always write a good old fashioned SQL query.

The fact is, cohort analysis is important, and it shouldn’t be that hard.  That’s why today, we’re introducing drag-and-drop cohort analysis in DataHero.  No coding, no pivot tables, no formulas.  Just drag-and-drop simple.

Oh, and did I mention it’s free?

To demonstrate the power of DataHero’s drag-and-drop cohort analysis, I’ll show you how easy it is to answer these three insightful questions:

  1. What is the breakdown of our monthly recurring revenue in Stripe based on the length of time someone’s been a customer?
  2. How are our MailChimp opens affected by when a user signed up?
  3. What is the breakdown of GitHub issues we’re closing each month based on when they were filed?

StripeStripe Monthly Recurring Revenue

Step 1: Connect DataHero to your Stripe account and import “Customers and Charges”

Step 2: Click Create a New Chart

 Create a New Chart

Step 3: Drag the following attributes onto the chart canvas:

  • Charge Created
  • Customer Created
  • Amount

That’s it!  You’ve instantly got a chart that shows you your monthly recurring revenue, broken down by when a customer was created:

Monthly Recurring Revenue

If you want to change the cohort size (for example, to weeks or quarters), it’s as easy as changing a dropdown:

Screen Shot 2014-07-15 at 4.32.12 PM

From here, you can further customize the analysis or the resulting chart using all of the options available on the chart canvas.

MailChimpMailChimp Opens

Step 1: Connect DataHero to your MailChimp account and import your campaign

Step 2: Click Create a New Chart

Step 3: Drag the following attributes onto the chart canvas:

  • First Open
  • Signup Timestamp

Done.  Now you’ve got a chart showing the number of opens for your email campaign over time, based on when users signed up:

MailChimp Opens

In this case, let’s click the Show Cumulative Chart toggle button in the top-right corner so that we can see the total number of opens, which is what we’re really interested in:

MailChimp Opens Cumulative

GitHubGitHub Issue Breakdown

Step 1: Connect DataHero to your GitHub account and import your issues (either for one repo or across your entire organization)

Step 2: Click Create a New Chart

Step 3: Drag the following attributes onto the chart canvas:

  • Closed
  • Created

Instantly, you’ve got a stacked column chart showing the tickets closed each month based on when they were filed:

GitHub Issues

What we really want to see is that as a percentage, so let’s click the Show as Percentage toggle button in the top left.  Let’s also change it to a stacked area chart, broken down by week instead of month:

GitHub Issues as Percentage

Getting Started with Drag-and-Drop Cohort Analysis

These are just a few examples of the insights you can get through cohort analysis.  DataHero’s drag-and-drop cohort analysis doesn’t just work with dates – you can also use categories, countries, and other attributes to segment and analyze your data.  It’s as easy as drag-and-drop!

DataHero helps you unmask the answers in your data. There’s nothing to download or install. Simply create an account and connect to the data services you use every day (like Salesforce, Stripe, MailChimp, and Google Drive). DataHero automatically decodes your data and shows you the answers you need through dynamic visualizations.

 

Create My First Cohort Analysis Chart With DataHero

By Chris Neumann

Create my Free DataHero Account

Get the fastest, easiest way to understand your data today.