---
title: "cohort analysis | Skills We Assign For | Azendo"
description: "Cohort and funnel analysis — separating behaviour from mix, and the Azendo roles assigned for it."
url: "https://azendo.co/skills/cohort-analysis/"
---

[Skills](https://azendo.co/skills/) Analytics and BI 

# cohort analysis.

Cohort analysis groups users by when they started and tracks each group over time. It separates changes in behaviour from changes in mix, which an aggregate metric cannot do.

## Where cohort analysis fits on a long engagement.

Aggregate retention is close to uninformative on a growing product. A month with many new users looks worse on retention simply because new users retain less than established ones, and a month with fewer looks better. Cohorting removes that confound and shows whether the product is actually improving for comparable users.

The pattern worth watching is whether later cohorts perform better than earlier ones at the same age. That comparison is the clearest available evidence that product changes are working, and it is invisible in any aggregate view.

## What an assigned team does with cohort analysis.

Cohort analysis needs event data with reliable user identity over long periods, which is an engineering property rather than an analytical one. Products that changed their identity model at some point have a discontinuity that quietly breaks every long-range cohort.

Getting that foundation right is why the analytics and the pipeline are usually scoped together under [data engineering outsourcing](https://azendo.co/services/data-engineering/) rather than separately.

## What we use cohort analysis for.

* Retention separated from growth mix Comparable groups tracked, so acquisition volume does not distort the retention picture.
* Product improvement evidenced Later cohorts compared against earlier ones at the same age.
* Funnel drop-off by cohort Where each group leaves the journey, rather than one averaged funnel hiding the differences.

## How cohort analysis capacity is assigned.

Cohort analysis capacity is assigned alongside the event pipeline it depends on, because identity continuity is an engineering property rather than an analytical one.

## Roles we assign cohort analysis for

* [Data Analyst Data science](https://azendo.co/services/data-science/data-analyst/)
* [Data Scientist Data science](https://azendo.co/services/data-science/data-scientist/)

## Service lines it sits in

* [Data science](https://azendo.co/services/data-science/)

Capacity is agreed as a committed monthly capacity across a discipline, not per skill.

## Related in analytics and bi

* [Looker — skill we assign for](https://azendo.co/skills/looker/)
* [Power BI — skill we assign for](https://azendo.co/skills/power-bi/)
* [Tableau — skill we assign for](https://azendo.co/skills/tableau/)
* [semantic layers — skill we assign for](https://azendo.co/skills/semantic-layers/)
* [A/B testing — skill we assign for](https://azendo.co/skills/a-b-testing/)
* [experimentation design — skill we assign for](https://azendo.co/skills/experimentation-design/)
* [causal inference — skill we assign for](https://azendo.co/skills/causal-inference/)
* [segmentation — skill we assign for](https://azendo.co/skills/segmentation/)

## Tell us what your roadmap needs cohort analysis for.

A service delivery manager replies with the disciplines we would assign, the monthly capacity and what the first month looks like.

[All skills we assign for](https://azendo.co/skills/)