Cohort Retention Calculator
Calculate age-specific weighted retention from complete or partially observed customer cohorts, without treating future unobserved periods as zero.
YOUR CALCULATION
Result
—
Calculation steps
Work through one step at a time or reveal the complete calculation. The steps use your current inputs.
How to calculate
For each cohort age, include only cohorts with a known retained count and divide their summed retained members by their summed starting members.
Retention(age)=Σ retained original members at age / Σ starting members for cohorts observed at that age
Worked example
At period 2, January retains 70 of 100 and February retains 120 of 200. Weighted observed retention is 190/300, or about 63.333333%. At period 3 only January is observed.
Assumptions and input details
Up to 100 unique cohort labels and 24 later periods. Counts are whole original cohort members and cannot increase. New customers and reactivation are excluded. A trailing - is unobserved, while zero is an observed complete loss. Cohort composition can change by age and make the aggregate rise even when individual cohorts decline. No future retention or lifetime value is predicted.
Using this calculator
Can I enter my own problem?
Yes. Replace the example values with your own inputs. The result, calculation steps, tables and applicable diagrams update from those inputs. Blank or invalid values clear the result; example values are never silently substituted for missing inputs.
Are the results exact?
Results use floating-point arithmetic and displayed rounding. Read the formula, assumptions and any stated data precision before interpreting the result.
Is my input uploaded?
The calculation runs in your browser. No account, file upload or external AI service is required. Inputs are not saved between page reloads.
Calculate finite and infinite geometric customer gross-profit value with explicit churn, discount timing, margin and acquisition cost.
Calculate NPS from rating-frequency counts, preserving passives in the denominator and showing every rating’s response share.
Compare two conversion proportions, percentage-point difference, relative lift, a pooled z statistic and a clearly labelled normal-approximation interval.
Reserved advertising space.