7.1
Cohort Retention Curves
The proportion of each joining group still active, plotted against time since joining.
No single originator; rigorous modelling lineage is Fader & Hardie
What it does
Plots what fraction of each joining cohort remains over time. One question only: does the curve flatten, or go to zero. The least dishonest indicator of product-market fit.
When it breaks
You cannot read flattening before enough time has passed. A curve drawn from three months of data is drawn from hope.
Case
The same Blue Apron disclosure carried the cohort curves: steep early decay with 62%+ churn inside six months. McCarthy used them in a customer-base valuation to challenge the IPO price directly, and the share price collapse subsequently vindicated the cohort read over the aggregate-growth narrative (see 9.1).
Wharton — a game-changing method for valuing companies ↗Diagram — not yet drawn
Three cohort curves: one flattening, one decaying to zero, one with too few periods to tell — the third labelled as the state most companies are actually in.
In the wild
Unvetted · not part of the tier assessment
What has been written about this tool in the last twelve months. Machine-retrieved and unchecked — everything above this line was checked.
Loading…