New: Cookbooks and AI ExplanationsStep-by-Step recipes to solve problems connected to Roadmaps and Cheat Sheets. Need more details? Use AI buttons for structured and simple explanations with concrete examples throughout the whole platform.Take a look
Every customer gets the exact same email, whether they bought yesterday or vanished a year ago.
What you'll have at the end
Customers scored and grouped by recency, frequency, and spend, with a name for each group like 'at risk' or 'champion'
You need
An orders table with a customer id, an order date, and an order amount on every row, covering enough purchase history to tell who buys often from who has drifted away.
Not covered
Discovering segments automatically with a clustering model like K-means; this recipe scores customers on three signals you can name and defend to a colleague, not a cluster a model chose on its own.
Leans on
Customers sorted into spending deciles for a campaign list
go there instead when marketing only needs one signal, total spend, ranked into buckets, not the combined recency-frequency-monetary picture.
Flag lapsed customers who've gone quiet
go there instead when the only question is a plain yes-or-no lapsed flag, not a full three-signal score.
The funnel step where most signups fall apart
go there instead if the group you're studying hasn't converted into paying customers yet; this recipe needs real purchase history to score anyone.
Checked 26 Aug 2026
Part of the Data Analytics cookbook