Skip to content
Module
Product and data

Cohort analysis: definition and examples

Cohort analysis groups users who share a characteristic at a given moment, most often their sign-up week or month, and then tracks their behavior over time. It compares groups at the same age in the product instead of a total that mixes long-time and brand-new users. The result usually takes the form of a cohort table or of retention curves by cohort.

Definition written by Alex Dionisio, Senior Product Manager. Updated November 13, 2026.

Why it matters for a PM

Aggregate metrics hide trends: a rising number of active users can mask worsening retention offset by acquisition. Cohort analysis shows a PM whether recent users stick around better than earlier ones, and therefore whether product changes have a lasting effect. It also helps compare segments or acquisition channels.

Example

A cooking app groups users by sign-up month and measures the share who cook at least one recipe a week four, eight and twelve weeks later. Cohorts that signed up after the onboarding redesign keep clearly more active users at eight weeks than earlier ones, while the overall active count had barely moved.

Key points

  • A cohort is defined by a shared event and a period: sign-up, first purchase, activation.
  • Read the table across rows (one cohort over time) and down columns (several cohorts at the same age).
  • Behavioral cohorts, such as users who invited a colleague, reveal the actions linked to retention.
  • A correlation between a behavior and retention does not prove causation.

Common mistakes

  • Comparing cohorts too small for the gap to be meaningful.
  • Forgetting that recent cohorts do not have data for longer periods yet.
  • Changing the definition of an active user between two analyses.

Go further with Module

The courses and lessons that cover this concept:

Guide on this topic

  • SQL for Product Managers

    The queries that let you decide on your own, the traps to avoid and AI for writing SQL, with a cheat sheet.