Description
Compare retention rates after a denominator revision.
Business timing and cohort summaries depend on event origins, bucket boundaries and the treatment of incomplete records. A time difference or bucket label is a supplied record convention rather than proof of customer behavior, completed service or future retention.
Compare retention rates after a denominator revision.
When to use this tool
Use Cohort Retention Denominator Delta when checking the stated business timing or cohort convention.
How to use the tool and how it works
- Enter retained, originalBase, revisedBase. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read oldRate, revisedRate, delta. Use the output convention below.
Compare retention rates after a denominator revision. Require positive whole original/revised bases and retained within both; oldRate = retained/original, revisedRate = retained/revised, delta = revised-old.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| retained | Retained | Required. Safe integer; minimum 0. |
| originalBase | Original Base | Required. Safe integer; minimum 1. |
| revisedBase | Revised Base | Required. Safe integer; minimum 1. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| oldRate | Old Rate | Required. Finite number. |
| revisedRate | Revised Rate | Required. Finite number. |
| delta | Delta | Required. Finite number. |
{
"input": {
"retained": 40,
"originalBase": 100,
"revisedBase": 80
},
"output": {
"oldRate": 0.4,
"revisedRate": 0.5,
"delta": 0.09999999999999998
}
}Limitations and assumptions
- The numerator stays fixed; no justified cohort revision, data correction or genuine behavioral retention change is established.
- Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
- Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.
Alternative or Complementary methods
Use complete event records and a defined cohort/period policy; evaluate commercial performance and uncertainty with appropriate complete analyses.
References
Similar or alternative tools
- Cohort Retention Reactivation Boundary
Partition a supplied unique cohort into retained, reactivated and inactive IDs.
- Cohort Revival Period Base Flag
Return retention share with an optional revived-customer base.