> For the complete documentation index, see [llms.txt](https://docs.churned.io/churned-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.churned.io/churned-docs/models/rfv-model.md).

# RFV model

Segmentation of users by recency, frequency and volume of product usage

## What it predicts

A usage **segment** per user: the same eight segments as the RFM model, but computed on product usage instead of purchases. It answers how engaged the individual users inside an account are, which is the earliest churn signal in SaaS.

## Data it needs

Usage events per user: logins, sessions, feature usage, transactions or API calls, delivered by a product analytics integration, a warehouse table or an event feed. Users must be linked to their account.

## How it works

For each user, **recency** is the time since the last usage event, **frequency** the number of active days or sessions in the period, and **volume** the depth of usage such as features used, time spent or transactions. Each is scored 1 to 5 relative to the other users, and the code maps to a segment with the same table as [RFM](/churned-docs/metrics-and-definitions/metrics/rfm-model-and-one-off-metrics.md#rfm-segments).

## How often it runs

Daily, with the previous segment stored per user.

## How to read the output

Look at the mix of user segments within an account: an account whose champions turn into hibernating users is at risk long before the contract ends. User-level segments are also the basis for the RFV segment playbooks under [RFV-Model Segment - Best Practices](/churned-docs/metrics-and-definitions/rfv-model-segment-best-practices.md).

## Where it surfaces

The Users page of SaaS dashboards, the account view, and audience conditions. The product-engagement part of the [health score](/churned-docs/models/health-scoring-model.md) uses the same usage data.