Editor’s Note: This post is co-authored by Ezra Freedman, Christina Jaworsky, and Eric Silberstein.
Our AI-powered Customer Lifetime Value feature, which we launched six weeks ago, makes predictions for individual customers.
We’re thrilled to announce that you can now export customer lifetime value predictions. In this post we show how to do that and explain calculations you can do to generate summary information for a list or segment.
Go to your list or segment and export to CSV.
Select customer lifetime value predictions from the end of the list of Klaviyo properties.
Churn risk prediction is exported as a number between 0 and 1. For example, 0.45 is 45%.
Predict future spending of a segment
Use a spreadsheet to sum the predicted customer lifetime value column. This will give you the expected revenue from customers in the segment for the next year.
Calculate average customer value
Compute your per-customer CLV for the segment by taking the average of the historical customer lifetime value or total lifetime value columns. This gets interesting when combined with specific cohorts. For example, create a segment that represents all customers who made their first purchase in the first three months of 2017. You can then calculate the average historical customer lifetime value and look at average predicted customer lifetime to estimate the future value of a cohort that is 18+ months old.
Estimate number of returning customers
First average the churn risk prediction column. Subtract that average from 1. Multiply this by segment size. This is the number of customers that are predicted to return. For example, if your average churn risk prediction is 0.8 and your segment has 10,000 customers, you can expect (1 – 0.8) x 10,000 = 2,000 to make a purchase in the next year.
Churn risk seem high?
You might be surprised at your average churn risk. We model churn risk based on your company’s data. Large numbers of one-and-done customers mean customers have a high probability of churn. Your lower churn risk customers are your more valuable customers and the Predictive Analytics tools can help you identify those customers. Read more about how we recently improved our calculation of churn probability here.
If you have ideas or want to share your thoughts about our work, our data science team would love to hear from you. Please send feedback to firstname.lastname@example.org.Back to Blog Home