top of page

[Throwback] Metrics Monday 01: Churn

I was first introduced to the idea of customer churn while freelancing for a marketing agency. One of their clients, a national chain of fitness clubs, needed to know what was driving up their churn rate, which had increased over the second half of the year. Though there are nuances and variations between and among companies and industries, the concept is fairly easy to grasp.




Salesforce provides the following succinct and helpful definition:

Churn rate, sometimes known as attrition rate, is the rate at which customers stop doing business with a company over a given period of time. Churn may also apply to the number of subscribers who cancel or don’t renew a subscription. The higher your churn rate, the more customers stop buying from your business. The lower your churn rate, the more customers you retain. Typically, the lower your churn rate, the better. 

Again, there are variations, but the calculation for churn rate is something like this:


customers lost during a time period / total number of customers at the beginning of the same time period


Case study


My imaginary (at least for now) gourmet noodles subscription service, Nicole’s Noodles, sends our customers 4 ounces of each of three different types of noodles every month. In June, our box contained hearty Japanese soba (buckwheat) noodles, light and delicate Italian fedelini, and quick and easy glass noodles.

 

We had 2,812 customers on June 1. We lost 271 customers between June 1 and June 30 (for simplicity’s sake, let’s say I didn’t enroll any new subscribers during that same period). My churn rate for June is 9.6%. Ouch. Maybe the buckwheat was too heavy for the summer.


How did I get there?

(271 [total customers lost June 1-30] / 2812 [total customers at the beginning of the time period] * 100 

With inflation and economic uncertainty on the rise, I would expect businesses providing non-essential goods and services will see increased customer churn if they haven’t already. That Sips by box might just fall victim to the budgetary axe but perhaps Celestial Seasonings or Bigelow will see higher sales from thrifty tea drinkers. 


Since customer churn is an actionable metric, analysts should be ready for stakeholders to request insights in this area. Take the initiative to lay the groundwork for calculating accurate, meaningful churn rates. Find your company’s data governance committee-approved definition of churn rate in your data dictionary.


I know, I know. You probably don’t have one of those, but perhaps you'll be the one to kick off an initiative to define your company’s key metrics! Data governance is fun, I tell you! In the absence of a formal definition, find the subject matter expert(s) on the topic. While you’re at it, find out how your company defines a customer. (Don’t laugh. Go ask a few different people in your organization to define a customer.)


Once you’ve defined “churn rate” and “customer”, don’t just calculate the metric. Dig into the data — what patterns do you observe? I’ll provide two straightforward examples, but consider as many factors as you can in the time available. 

  1. Despite a number of lost newer customers, does your company have a large number of loyal customers? One possible recommendation could be to focus on long-time customer retention rates by investing in that segment of customers. 

  2. Have organizational events impacted churn? Maybe the customer experience team overhauled their processes and started using a new service management platform last month, and as the team was adjusting to the new workflow and new software, their turnaround times increased and customer satisfaction rates decreased as a result.


And that's all there is to it!


This post originally appeared in SELECT * FROM data; on Medium and Substack on July 18, 2022. Lightly edited upon migration to this site on Jan. 15, 2024.


If there is a metric you'd like me to demystify, comment below or find me on Bluesky, Mastodon (@nicolemark@vis.social), the Women in Dataviz Slack (request an invite), the Data Visualization Society Slack, or LinkedIn.


コメント


bottom of page