Measure retention by cohort
Group customers by first purchase period or acquisition route. Compare the share returning at the same elapsed time so that new customers have equal opportunity to reorder.
Worked example
If 30 of 100 January households buy again within 60 days and 40 of 200 February households do, the second cohort retains 20% versus 30%. A larger count of returning households can hide weaker retention.
Change the assumption
Would you call February’s 40 returners an improvement over January’s 30?
Check the reasoning
February produces more returning households but a lower repeat rate at the same age. Check acquisition cost and cumulative contribution to see whether that larger cohort was economically better.
Check your reasoning
Should gift purchases count in the household cohort?
Reveal the explanation
Segment gifts when the purchase occasion affects repeat behaviour. Report the segment definition, denominator and observation window with the result.
Try the same framework in a different case
Explore worked stories in the reading room · Practise the next analysis