An analytics technique that groups users by a shared attribute (usually signup date or first purchase) and tracks how each cohort's behavior evolves over time — separates trends from compositional shifts.
Cohort Analysis isolates time-based effects from population-mix effects. A simple example: monthly cohorts of new users plotted by month-since-signup retention — Jan 2024 cohort had 40% Month 6 retention, Feb 2024 had 45%, etc. This surfaces real product improvements that aggregated metrics hide. Cohort Analysis is standard in subscription businesses (retention curves), marketplaces (LTV by acquisition month), and any product where user behavior evolves with tenure.
Discovering that a UX change improved Month 1 retention from 40% → 55% via cohort retention curves — the aggregate retention number was flat because the new cohorts were small.
Cohort Analysis is the single most important analytics technique for any subscription or user-driven business — aggregated metrics regularly hide what cohort views make obvious.
Need help implementing this in your business?
Get Started