What Is Cohort Analysis?
Cohort analysis groups customers by shared characteristics or time periods to track how their behaviour changes over time. Learn how it reveals retention and growth patterns.
Key Takeaways
- Cohort analysis groups customers who share a common characteristic (usually acquisition date) and tracks their behaviour over subsequent periods.
- It reveals whether your business is genuinely improving — are newer cohorts retaining better than older ones?
- It separates growth effects from retention effects, preventing misleading aggregate metrics.
What cohort analysis is
A cohort is a group of customers who share a defining characteristic within a specific time period. The most common cohort type is acquisition-based: all customers who made their first purchase in January 2025 form one cohort. Cohort analysis then tracks that group's behaviour — purchases, retention, revenue — over subsequent months. By comparing cohorts, you see whether January customers behave differently from February customers, and whether your business changes are improving outcomes.
Why aggregate metrics mislead
Overall metrics like total active customers or average revenue can mask serious problems. If you are acquiring 1,000 new customers per month but losing 800 from previous months, aggregate active users still grow — but retention is terrible. Cohort analysis exposes this by tracking each month's customers independently. You see exactly what percentage of January's customers are still active in month two, three, and twelve. This visibility is impossible with aggregate numbers alone.
Reading a cohort table
A cohort retention table has rows representing each cohort (usually by month) and columns representing time periods after acquisition. Each cell shows the percentage of the cohort still active in that period. If January's cohort shows 60% retention at month one and 30% at month six, while March's cohort shows 70% and 40% for the same periods, your retention improved between January and March. Downward-sloping patterns reveal natural churn rates; improvements in later cohorts indicate positive business changes.
Applying cohort analysis
Compare retention curves across cohorts to evaluate the impact of product changes, pricing adjustments, or onboarding improvements. For African subscription businesses or ecommerce platforms, cohort analysis reveals whether investments in customer experience are translating into better retention. Segment cohorts by acquisition channel to identify which channels bring the most durable customers. Track revenue per cohort to see whether customers are spending more or less over time.