Churn Data Science Strategy Churn Data Science Strategy
Editor’s note: Carl Gold is a speaker for ODSC West 2022 this November 1st-3rd. Be sure to check out his talk,... Churn Data Science Strategy

Editor’s note: Carl Gold is a speaker for ODSC West 2022 this November 1st-3rd. Be sure to check out his talk, “Fighting Churn With Data,” there!

Churn means that your customers cancel your service, or stop spending money on your site or app. Churn is the most common data science problem in the world. That’s because nowadays every company has a churn problem! All companies want to keep their customers coming back.

Top 3 Challenges for Data Science with Churn

Most data scientists have fit a churn model in a class or bootcamp. But really fighting churn is much harder than it sounds.

  1. Churn is hard to predict. It may be easy to know a customer is at risk. But it is very hard to predict the timing. There is too much randomness and stuff you don’t know.
  2. Churn is harder to prevent. Because customers know the product. You can’t fool them with marketing.
  3. Churn is Hard to communicate about and organize around.

Your churn strategy can use data science, but it’s not as simple as it sounds.


Churn Data Science Strategy Pyramid

You can think of your churn data science strategy like a pyramid.

  • The foundation is event data. You store it in a data warehouse or data lake house. It’s like a foundation in a house, because you need to have it but a foundation alone does not do that much for you.
  • The first level is calculating customer metrics. You will use customer metrics for feature engineering in a model, but they have many more uses in your company. This level also includes calculating your churn rate.
  • The next level is to do basic segments and targeting using your metrics. A/B testing is also done at this level.
  • The pinnacle of the pyramid is AI. Or machine learning, or automation – whatever you want to call it. This is the most advanced level. AI for automated churn reduction has a lot of pitfalls – your actions will create bias in the model. You need to constantly retrain, and include information about your actions in the model. Reinforcement learning is a natural fit for optimizing the impact of interventions.

Churn Data Science Strategy Pyramid

The Good News

You can get a lot of good results with not that much effort. You may have heard of the Pareto principle: 80% of the effect from 20% of the causes. People take it to mean you can get a lot from a little effort. It’s not quite that good with churn and data science. But consider the pyramid above.

  • You can get 50% of possible churn reduction with 25% of the effort. That corresponds to Calculate churn and customer metrics from data and look at them
  • You can get 75% of possible churn reduction with 50% of the effort. That means interventions targeted by simple metrics and some low complexity A/B testing.
  • To get the maximum possible churn reduction using AI/ML and automation is 50% more of the total effort.

Get More Info

About the author/ODSC West speaker:

Carl Gold is currently the Data Science Director at OfferFit.ai, an AI-as-a-Service reinforcement learning engine that maximizes customer upsell and retention. Before coming to OfferFit, Carl was Chief Data Scientist of Zuora, the Subscription Economy’s leading billing platform. Based on his experiences fighting churn for SaaS companies during his time at Zuora, Carl wrote the first book dedicated to customer churn analytics and data science: “Fighting Churn With Data”. Carl has a PhD from the California Institute of Technology and first author publications in leading Machine Learning and Neuroscience journals.

ODSC Community

The Open Data Science community is passionate and diverse, and we always welcome contributions from data science professionals! All of the articles under this profile are from our community, with individual authors mentioned in the text itself.