How to Analyze Cohort Data
How to analyze cohort data means grouping users by a shared starting event — typically signup date or first purchase — and then tracking what percentage of each group remains active, paying, or engaged across subsequent periods. The output is a table where each row is a cohort and each column is a period after the starting event.
Build a cohort retention table from your user or subscription export without writing SQL or setting up a BI tool
Drop your file in and ask a question — no account needed.
Upload your spreadsheet.xlsx .xls .csv — free to try, no accountWhat this export contains
| User ID |
| Signup Date |
| Last Active Date |
| Plan |
| Status |
| Month 1 Active |
| Month 2 Active |
| Month 3 Active |
| Revenue |
| Cohort Month |
What usually goes wrong with it
Building a cohort table in Excel requires a multi-step pivot setup
A cohort retention table in Excel requires: grouping users by signup month, counting active users per subsequent month per cohort, calculating percentages, and formatting as a matrix — at least four steps that most non-technical analysts spend 2+ hours on the first time.
DataMimi Datamimi groups users by Cohort Month column and calculates the retention percentage for each subsequent period, returning the matrix format directly without a pivot table setup.
Cohort data requires multiple period snapshots joined by user ID
To see how January signups retained through June, you need active user data for January, February, March, April, May, and June — each as a separate snapshot — joined by User ID. Assembling six exports manually is a common bottleneck.
DataMimi It accepts up to six monthly exports in a single session, joins them by User ID, and builds the retention table from the joined data without requiring a manual assembly step.
Cohorts with small sizes produce misleading retention percentages
A cohort of 12 users losing 1 person shows an 8.3% churn rate. A 1-person variance produces a wildly different percentage than a cohort of 200 users losing 1 person. Small cohorts need to be flagged before trend conclusions are drawn.
DataMimi Datamimi flags cohorts below a minimum size threshold (configurable) in the output table so that statistically noisy rows are clearly labeled before you draw trend conclusions.
Common questions
How to analyze cohort data from a user export without SQL?
Group users by signup month using a MONTH(Signup Date) formula. For each subsequent month, count users from each cohort who were still active. Divide active count by cohort size for the retention percentage. Or upload to Datamimi and ask for a cohort retention table.
What is a good cohort retention rate for SaaS?
Month-1 retention (users active in month 2) of 60–80% is considered strong for consumer apps; B2B SaaS typically retains 80–90% in month 1. By month 6, strong consumer apps retain 25–40%; B2B products 60–75%. Track your own baseline before comparing to benchmarks.
What columns do I need to build a cohort retention analysis?
At minimum: User ID, Signup Date, and a column that marks whether the user was active in each subsequent period. Active status can be a date (Last Active Date) or a boolean column (Month 1 Active, Month 2 Active, etc.).
What does Datamimi cost?
Free: $0/month, 40 credits, no credit card required. Lite: $9/month, 400 credits. Starter: $24/month, 1,500 credits, up to 3 simultaneous files. Pro: $59/month, 5,000 credits with rollover. Team: $199/month, 20,000 credits, 5 users.
Try it with your own file
DataMimi reads the file you actually have — merged cells, headers below row one, totals pasted at the bottom — and shows which rows and columns every number came from.
Ask about your file