The Retention Curve
5 min read · 4 principles · apply it by lunch
Morning. Every cohort you’ve ever acquired is still telling you something. Almost nobody plots it.
Take the customers you won twelve months ago and plot what share of them are still here, month by month — does that line reach a floor anywhere, or is it still on its way to zero? One of those answers means you own a business. The other means you’re renting one from your ad account, thirty days at a time.
Peter Fader, professor of marketing at the Wharton School, and Bruce Hardie, professor of marketing at London Business School, have spent decades building small probability models of how customers actually behave; their 2009 overview in the Journal of Interactive Marketing, Probability Models for Customer-Base Analysis, is the readable summary of that work. One finding in it should change how you read every retention chart you’ll ever see. Within a single cohort, the retention rate almost always rises as the cohort ages — a higher share of the month-twelve survivors make it to month thirteen than the share of month-one survivors who made it to month two — and it happens without a single customer becoming more loyal. The mechanism is sorting. Your cohort was never one kind of person. It was a mix of people with very different propensities to leave, and the ones most likely to go, go first. What remains once the fragile have gone is a residue of the durable, so the aggregate rate climbs even if nobody’s behaviour has changed at all. That’s why the curve bends. The only live question is where it stops bending, and whether it stops at all.
The Retention Curve is Day 187 of 365.
In the Daily, each of its four principles is explained in full, with a one-page template to apply it the same day. A new framework arrives every morning at 7am for a year, across all fifteen courses of the FutureMBA curriculum.
$29 a month · cancel any time · 7-day money-back guarantee