The article outline the options that are available to define churn within the subscription option in the customer churn template.
The customer churn prediction template offers an end-to-end solution for predicting whether a customer will churn in the near future using existing data. In the subscription option, users need to specify additional details about the business' definition of churn. More precisely, they will need to determine the specific time frames that define the three prediction labels in their businesses:
-
“too late” → customers classified as “too late” are hard to retain because they have a high chance of leaving soon and interventions are ineffective
-
“about time” → customers classified as “about time” could be retained with timely interventions
-
“safe” → customers classified as “safe” do not require any immediate actions
The template also allows users to customize their ML solution according to the business' definitions of “too late“ and “about time“, by allowing them to adjust the periods, as shown in the screenshot below.
Define churn period in the template