GOJI
All terms
DataReviewed by Joe S.

Cohort analysis

Cohort analysis groups customers by when they joined and follows each group over time: how the January signups behaved by month three versus the April ones. It separates real change from the blur of averages.

Why it matters

Blended metrics smear the past over the present: retention can be collapsing for new customers while the overall average looks fine, propped up by loyal old-timers. Cohorts reveal whether things are getting better: the question every strategy change begs.

How it works

Each row is a joining period, each column an age; cells show survival, spend or activity at that age. Reading down a column compares generations at the same life stage: the clean way to see if the new onboarding, pricing or positioning changed anything.

What to do about it

After any significant change, judge it by cohorts: do customers acquired after behave differently at the same age? It's the closest thing marketing has to a before-and-after experiment.