Quick answer
A retention curve is a chart of the percentage of a user cohort still active after each day, week or month since they started; a curve that flattens shows a stable base of users who keep getting value.
Formula: Day-N retention = cohort users active on day N ÷ cohort size × 100
What is a retention curve?
A retention curve is a line chart that shows the percentage of a group of users (a cohort) who are still active after each day, week or month since they started. The x-axis is time since the start event (day 0, day 1, day 7…); the y-axis is the share of the cohort that came back. It always starts at 100% and falls; the question is how fast and whether it levels off.
Retention curves are one of the clearest signals of product-market fit: a curve that flattens means a stable group of users keeps finding value, while a curve that keeps sliding toward zero means users eventually leave.
How to read a retention curve
| Shape | What it means | Typical cause |
|---|---|---|
| Steep early drop, then flat | Many users try once; those who stay, stay | Normal for most apps; improve onboarding to raise the plateau |
| Steady decline to zero | No lasting value for any segment | Weak product fit or wrong audience |
| Flat early, drop later | Users churn after a trial or a content run-out | Trial end, pricing, or limited depth |
| Rising later (smile curve) | Users return after a gap | Seasonal use, new features, re-engagement |
| Newer cohorts higher | Product is improving | Onboarding or feature changes working |
How to calculate retention
Day-N retention = users from the cohort active on day N ÷ users in the cohort × 100
Variants:
- N-day (exact) retention: active exactly on day N.
- Unbounded (rolling) retention: active on day N or any later day; gives higher numbers.
- Bracket retention: active within a range, such as week 2 (days 8–14).
Always state which variant and which activity definition (any event or a core action) you use.
Worked example
A cohort of 1,000 new users who signed up in the first week of March (sample data), active = completed a lesson:
| Day | 0 | 1 | 7 | 14 | 30 | 60 | 90 |
|---|---|---|---|---|---|---|---|
| Active | 1,000 | 340 | 210 | 180 | 160 | 150 | 145 |
| Retention | 100% | 34% | 21% | 18% | 16% | 15% | 14.5% |
The curve drops steeply in the first week and flattens around 15% after a month: about 145 of every 1,000 sign-ups become long-term users. Raising day-7 retention from 21% to 25% through better onboarding would likely lift the whole plateau.
Retention curves in TapCub
The retention report shows cohorts by start date with a count and rate per period, a size-weighted average line, and three modes: returned on period N exactly, on period N or later, and period counts. You can choose the start and return events, the period (day, week, month) and up to 30 days or 12 weeks or months. See how to do cohort analysis.
Related terms: retention, cohort, churn, behavioral cohort.
Sources
- Mixpanel Docs. Retention reports.
- Amplitude Docs. Retention analysis.
Was this explanation clear?
We use your answers to fix and expand this page.
Couldn’t send. Please try again in a minute.
Thanks for the feedback. We’ll use it to improve this page.You’ve already sent feedback on this page. Thanks.
Data Analyst
Explores traffic sources, conversion funnels, and retention, using clear metric definitions and concrete examples to explain what the numbers mean.