In plain words
A cohort is a group of customers who started at the same time, such as everyone who subscribed in March. Cohort analysis follows that group forward: how many are still subscribed after one month, two, six, and how much profit they have produced along the way.
It separates two things that a monthly total blends: how well you keep customers, and how many new ones you added. A business can grow its revenue every month while each cohort does worse than the last. Only the cohort view shows it.
Formula
- Share remaining at month m = customers of the cohort still active ÷ customers it started with
- Cumulative profit per customer at month m = Σ margin of the cohort's orders so far ÷ customers it started with − acquisition cost
Worked example
A cohort of coffee subscribers acquired for $30.00 each. The engine's projection has 70.0% of them still subscribed after the first month, 47.6% after three, 33.0% after six and 17.4% after twelve.
Per subscriber, the cohort stands at −$26.21 after the first order, −$5.93 at month three, $7.11 at month six and $23.29 at month twelve.
The example order
A $40.00 bag of coffee, shipped free, every cost counted
2 declared kinds cost nothing on this option
| Step | Grain | Amount |
|---|---|---|
| Revenue | – | $40.00 |
| Cost of goods | per unit | −$12.00 |
| Pick and pack | per order | −$1.18 |
| Packaging | per parcel | −$0.50 |
| Shipping label | per parcel | −$7.50 |
| Card fee per order | per order | −$0.30 |
| Refunds | percent | −$2.00 |
| Card processing | percent | −$1.16 |
| Contribution margin | – | $15.36 |
| 2 kinds costing nothing | – | $0.00 |
Computed by the margin engine in Offer Suite's own code, in whole cents, from a $40.00 bag of coffee with a $12.00 unit cost.
A cohort is not a segment
A cohort is defined by when its customers started. A segment is defined by something else about them: where they came from, what they bought. You can cut a cohort by segment, but mixing start dates inside one group blends new customers with old and hides how retention is changing.
Using it
Build cohorts by start month and by the offer that won them. Compare the same month of life across cohorts: month three of March's subscribers against month three of April's. If newer cohorts fall away faster, something changed in how you acquire them, often a deeper discount that brought less committed buyers.
In Offer Suite
Offer Suite links each renewal to the first order whose cart started the subscription, so renewals are attributed to the option that won the subscriber. Its simulator projects a cohort month by month from a renewal curve the brand supplies.
Source: Offer Suite's offer simulator.