What is cohort analysis?
Cohort analysis groups users by when they joined or what they did, then follows each group over time. How to read the grid, with a worked example.
What is cohort analysis?
Cohort analysis groups users by something they share, usually the week or month they signed up, then tracks each group separately over time. Because every group is followed on its own clock, it separates changes in the product from changes in who you acquired, which a single average always hides.
A worked example.
Three signup cohorts of a SaaS product, week 4 retention.
| June cohort, 900 signups | 27% still active at week 4 |
|---|---|
| July cohort, 1,150 signups | 29% still active at week 4 |
| August cohort, 1,400 signups, new onboarding shipped | 38% still active at week 4 |
| Blended average across all three | 32% |
The August cohort is 11 points better than June, and the blended average shows none of it
The blended number is dragged down by cohorts that predate the change. Reading down the week-4 column is how you see whether the new onboarding worked, weeks before the average catches up.
Why averages hide what cohorts reveal
A site-wide retention number mixes people who joined last week with people who joined two years ago. Those groups were acquired through different channels, onboarded through different flows and used different versions of the product. Averaging them produces a number that describes nobody.
The problem gets worse as you grow. Rapid acquisition floods the denominator with brand-new users who have had no time to retain, so a company doing everything right can watch its blended retention fall while every individual cohort improves.
Cohorts fix this by refusing to mix. Each group is followed from its own day zero, so week 4 for the June cohort and week 4 for the August cohort are genuinely comparable.
How to read a cohort grid
The grid has two readings and both matter.
Along a row you see one cohort decaying over time. The question is whether the curve flattens. A curve that drops and then goes horizontal means you have found people for whom the product is genuinely durable. A curve sliding toward zero means nobody sticks, and acquisition spend will not fix it.
Down a column you see the same age across successive cohorts. This is the one that tells you whether recent work helped. If week 4 improves cohort after cohort, something you shipped is working, and you know it long before any blended metric moves.
The diagonal is the trap. Bottom-right cells contain the newest cohorts at their oldest ages, which means they are always based on tiny numbers. Ignore anything with a small denominator.
Acquisition cohorts and behavioural cohorts
Two ways of forming the group. Acquisition cohorts are the default; behavioural cohorts answer harder and more useful questions.
| Acquisition cohort | Behavioural cohort | |
|---|---|---|
| Grouped by | When they first arrived or signed up | An action they took, such as inviting a teammate |
| Answers | Is the product getting better over time? | Which behaviour predicts that someone stays? |
| Typical use | Tracking the effect of onboarding changes | Finding the activation moment worth designing for |
| Watch out for | Seasonality and channel mix between cohorts | Correlation read as causation: engaged users do more of everything |
The classic behavioural finding, a social network noticing that users who added a threshold number of connections in their first week almost never left, came from a behavioural cohort, not an acquisition one.
See it on real data
The live demo is a fully populated dashboard with real demo traffic. No signup and no card required.
Open the live demoGetting cohort analysis right
Match the interval to the product
Daily cohorts for consumer habit products, weekly for team tools, monthly for anything invoiced monthly. The wrong interval makes a healthy product look broken.
Define active as value delivered
Counting logins flatters every curve. Count the action people pay for: a report run, a message sent, an invoice issued.
Ignore small cells
A cohort of 30 with two survivors is not a 7% retention rate, it is noise. Set a minimum size and grey out everything below it.
Annotate the grid
Mark the week a pricing change, a big campaign or a new onboarding shipped. Without annotations you will find a step change and spend a day rediscovering what caused it.
Cohorts in Mrkr
Mrkr's cohorts are behavioural rather than acquisition cohorts. You define a group from up to eight conditions covering session attributes, events fired or never fired, paths viewed, lifetime sessions, pageviews or revenue, first-seen recency and conversion state. Membership is resolved and stored, so the cohort can then be applied as a filter on any other view.
What Mrkr does not draw is the grid this page describes. There is no acquisition-cohort retention triangle with a signup week on each row and a week since signup on each column, and no sequence conditions of the did A then B within three days form. If that specific artefact is a requirement, a product analytics tool built on a columnar store is the better fit and you should weigh that properly.
Following any cohort across weeks also needs identity that persists beyond a day, which the default cookieless mode deliberately does not provide: its identifier rotates daily so nobody can be followed. For cohort work you either enable the optional per-site cookie mode, which requires a consent banner on that site, or you send your own user id with events for signed-in users.
For a logged-in product the second route is usually better anyway. Your backend already knows who did what, and the id survives a device change.
Questions, answered.
Related terms.
- What is retention rate?
Retention rate is the share of users from a starting group who are still active at the end of a defined period.
- What is churn rate?
Churn rate is the share of customers, users or revenue lost during a period.
- What is dau/mau ratio?
DAU/MAU is daily active users divided by monthly active users, expressed as a percentage.
- What is product analytics?
Product analytics is the measurement of what people do inside a product rather than how they arrived at it.
- What is event?
An event is any recorded action beyond loading a page: a button click, a form submitted, a video played, a subscription upgraded.
Where this shows up in Mrkr
- Build cohorts from your own events in Mrkr
Behavioural cohorts from up to eight conditions, applied as a filter on any view.
- See the retention curves those cohorts produce
- Browse the full analytics glossary
Every metric, method and privacy term, defined in one place.
Your first visitor is already here.
Drop in the script and watch them land. It takes about a minute.