Keep Still-Open Order Cohorts Out of a Settled Return-Rate Denominator — Free
Fresh deliveries have had less time to produce returns. Keep their early observations visible but separate from an explicitly matured denominator before presenting a settled return rate to an operations team.
The proof surface
Monthly churn tools pool a different subscription event. This register checks return cohorts with unequal observation age, retaining open units and early returns separately. It exposes the maturity assumption rather than treating every delivery as equally observed.
InputDelivery cohort | age in whole days | delivered units | returned units observed; supplied observation-maturity window (days)
Rare deviceMonthly churn tools pool a different subscription event. This register checks return cohorts with unequal observation age, retaining open units and early returns separately. It exposes the maturity assumption rather than treating every delivery as equally observed.
Output artifactPooled observed rate in matured cohorts with row-by-row context
Cost$0 local calculation · no card, paid key, subscription or signup · proposed filing price is not for sale
Sample, not your facts: Illustrative inputs: Cedar deliveries | 40 | 100 | 8; Maple deliveries | 35 | 50 | 2; Pine deliveries | 10 | 80 | 1. Supplied observation-maturity window (days) = 30. Pooled observed rate in matured cohorts: 6.666667 % settled-cohort returns. All records are invented.
Before using the mature-cohort register
Choose and document an observation window appropriate to the question, not a window that makes the result look favorable. The sample thirty days is a hypothetical reporting convention, not a customer-rights deadline. Use delivered units as the count basis and apply it consistently: units, orders and customers are not interchangeable. Age is measured from the cohort's defined delivery date to one common reporting date. Returns are observed returned units from that same cohort and cannot exceed delivered units. Exclusions affect both sides of the settled rate. Reporting delays, exchanges, partial orders and later returns can still limit interpretation; reaching the chosen window does not establish that every eventual event has been captured.
Why the flat version breaks
Including open deliveries only in the denominator
Adding fresh units while retaining only settled returns pushes the rate downward mechanically. Exclude an open cohort's numerator and denominator together under this convention. Its early returns remain visible as context, so the exclusion cannot be mistaken for an absence of returns.
Averaging cohort percentages
A cohort of fifty units and one of a thousand are not equal-sized observations. The settled rate pools counts, not the displayed row percentages. A simple mean can overstate the contribution of a small cohort and obscure the actual number of units behind the rate.
Calling the chosen window a legal return limit
Reporting maturity and customer return rights are different concepts. The app neither reads policies nor determines whether a later return must be accepted. Keep the maturity label statistical and verify consumer-policy questions with the responsible team or qualified adviser.
How to work the mature-cohort register
Define the cohort and reporting cutoff
Keep one cohort definition across the register, such as delivery date under a documented calendar convention. Record the reporting date privately and calculate whole-day ages consistently. Mixed shipping and delivery dates do not belong in one age model. Anonymous cohort codes are enough; customer names, addresses and order identifiers are unnecessary.
Reconcile counts within each cohort
Enter positive whole delivered units and whole observed returned units from zero through the delivered count. Clarify whether exchanges and repeat returns count as one returned unit. Do not count a refund for an undelivered cancellation as a delivered-unit return. Missing event data is not a zero, and a return from another cohort cannot be borrowed to fill a gap.
Apply maturity to numerator and denominator
Include a cohort when its age is at least the supplied window. Sum returned units across included cohorts, sum their delivered units, then divide returns by deliveries and multiply by 100. Keep open cohorts' delivered units and early observed returns in separate context metrics. Averaging cohort percentages would weight small and large cohorts incorrectly.
Publish the window with the rate
Describe the count basis, reporting date, included mature units and open units alongside the percentage. Have the operations owner confirm that observations are complete enough for the intended decision. Changing the maturity window creates a different statistic, not proof of operational improvement. A rate comparison needs comparable cohorts and reporting conventions.
What the mature-cohort register separates
Question
Before
Inspect this instead
Including open deliveries only in the denominator
Adding fresh units while retaining only settled returns pushes the rate downward mechanically. Exclude an open cohort's numerator and denominator together under this convention. Its early returns remain visible as context, so the exclusion cannot be mistaken for an absence of returns.
Reconcile counts within each cohort
Averaging cohort percentages
A cohort of fifty units and one of a thousand are not equal-sized observations. The settled rate pools counts, not the displayed row percentages. A simple mean can overstate the contribution of a small cohort and obscure the actual number of units behind the rate.
Apply maturity to numerator and denominator
Calling the chosen window a legal return limit
Reporting maturity and customer return rights are different concepts. The app neither reads policies nor determines whether a later return must be accepted. Keep the maturity label statistical and verify consumer-policy questions with the responsible team or qualified adviser.
Publish the window with the rate
This mature-cohort register replaces a manual count or calculation, not source verification or the responsible person’s review.
Run it on the samples, right here
FIRST-LOAD
HYPOTHESIS / PROTOTYPE — checkout unavailable. Calculation is local. A draft is saved automatically in this browser profile when storage is available; Reset to sample clears it. Optional Pro history stores only five summaries and has its own deletion control. State links encode your inputs and can remain in browser history, clipboard or recipients’ records; share only non-sensitive rows. Optional external AI formatting leaves this device. The required site analytics beacon reports page activity; shared URLs contain encoded inputs. Do not treat an encoded URL as private. The calculator has no input-collection endpoint.
Reporting arithmetic only, not a forecast, return-rights interpretation or proof of complete data. Ask the operations owner to confirm cohort definitions, reporting delays and the count basis before publishing or comparing this statistic.
Data note: The mature-cohort register processes Delivery cohort | age in whole days | delivered units | returned units observed locally. Starter/sample selection and Run compute in this tab; no input is sent by the calculator. A local draft may be saved; explicit state-link sharing or optional external AI formatting can disclose inputs. Use non-sensitive labels.
Go deeper: the companion app files the same reading as a bound register page
The article demo above runs without limits. The companion app keeps a local history, exports the rows as CSV, prints the mature-cohort register reading, and holds your drafts on this device — one complete free app run; the proposed $4 one-time filing layer is not for sale.
The mature-cohort register answer stays complete for free. The proposed $4 one-time filing layer adds row CSV, print and five local reading summaries, not hidden answers. Checkout is unavailable; the article demo remains unlimited.
Reporting arithmetic only, not a forecast, return-rights interpretation or proof of complete data. Ask the operations owner to confirm cohort definitions, reporting delays and the count basis before publishing or comparing this statistic.
What this is built on
Method: Include a cohort when its age is at least the supplied window. Sum returned units across included cohorts, sum their delivered units, then divide returns by deliveries and multiply by 100. Keep open cohorts' delivered units and early observed returns in separate context metrics. Averaging cohort percentages would weight small and large cohorts incorrectly.
All sample records, dates, quantities and labels are invented. No outside policy, contract, rate, clock offset, measurement or accessibility standard is represented as verified.
Google’s official pricing documentation, fetched 2026-10-01, says AI Studio is free in available regions. Optional formatting may require a Google account; manual local entry requires none. Limits can change and free-tier content may be used to improve products. Do not send private records.
Before: fresh deliveries diluted a supposedly settled percentage. After: mature counts and still-open observations have separate denominators.
Three worked readings, with different inputs
Sample A — typical inputs
Cedar deliveries | 40 | 100 | 8
Maple deliveries | 35 | 50 | 2
Pine deliveries | 10 | 80 | 1
Cedar and Maple have reached the supplied thirty-day observation window. Their ten observed returns divided by 150 delivered units give 6.666667%. Pine has one early return among eighty deliveries but is still open under this convention; both its numerator and denominator are excluded from the settled rate. Its observations remain visible in the register rather than being discarded or described as zero future returns.
Fir supplies a settled rate of 10/200 = 5%. Rye's eight early returns are visible, but its entire cohort remains outside the settled denominator because only fifteen days have elapsed. Combining all eighteen returns with all three hundred deliveries would give 6%, which answers a different mixed-age question. The register does not forecast how many more Rye returns will arrive.
A cohort at exactly thirty days is included because the supplied maturity rule is age greater than or equal to the window. Its forty units and zero observed returns give a zero settled rate. That does not prove the cohort can never return items later or that reporting is complete. With no matured cohort at all, the tool rejects the missing denominator rather than printing a misleading zero rate.
Optional AI formatting, never the calculation
Manual entry completes this mature-cohort register for free without signup. If available to you, the free AI Studio interface linked in the sources may format fictional or non-sensitive notes; external access may require an account. No API key or AI call is built into this tool. Free-tier content may be used to improve products. Review each cell and transcribe it to the labeled row schema; do not paste the JSON object into the row box.
Format only these fictional or non-sensitive notes for a mature-cohort register. Return strict JSON shaped as {"rows": [{"label": "string", "cells": ["string", "string", "string"]}], "setting": "string"}. The columns are Delivery cohort | age in whole days | delivered units | returned units observed; the setting is Supplied observation-maturity window (days). Keep all supplied strings and quantities exactly; do not calculate, infer missing entries, invent dates or add advice. If any required value is missing, return an empty rows array and ask me for it separately. I will verify every cell against my source and manually transcribe rows using vertical bars before running the local calculator.
An AI response is not executed, fetched or trusted as a result. Missing values remain questions; the strict local parser checks the rows you actually enter.