> For the complete documentation index, see [llms.txt](https://docs.mediarithmics.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mediarithmics.io/audience-and-activation/build-your-audiences/target-users-by-affinity-and-intention.md).

# Target users by affinity and intention

Build audiences on the Stories scores: users in an active purchasing cycle, and users with a lasting interest in a product category.

## Your goal

Reach the users a campaign should actually go to - the ones in an active purchasing cycle right now, or the ones with a lasting interest in a product category - using scores the platform maintains for you rather than criteria you have to invent.

## Expected outcome

Segments built on a **Stories** score, combined with your own criteria, and refreshed as the scores are: both are recalculated as soon as a session ends and new events are ingested.

## When this is useful

* A campaign is tied to one product category - a launch, a promotion, a seasonal push - and you need the audience that cares about that category.
* Your trigger campaigns have run out of cart abandoners and you need fresh, incremental volume earlier in the journey.
* A recurring communication - the weekly newsletter, an anniversary email, the homepage - should adapt to each user's preferences instead of carrying the same content for everyone.
* You want to size an addressable audience before committing a budget to it.

## Prerequisites

* **Stories enabled on your account.** It is not on by default. Your Customer Success Manager needs the product scope - a category for Intention, a category or a brand for Affinity - and the channels the scores should cover.
* **The events the algorithms read, carrying the right properties.** Product view, add to cart and purchase, with `category` and `product_id` for Intention, and `category`, `unit_price` and `quantity` on the purchase for Affinity. The full table is on [Affinity & Intention](https://app.gitbook.com/s/XSPACE_SETUP/plan-and-integrate/set-up-advanced-features/affinity-and-intention-ml-algorithm#prerequisites) in the `Setup & Monitor` section.
* **A builder.** The scores are available directly in the [segment builders](/audience-and-activation/build-your-audiences/segment-reference/segment-builders.md), so no query language is required.

## Concepts you need first

| Concept                     | Where it is defined                                                                                                                                                                                                                                       |
| --------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Stories, and the two scores | [Stories: ready-made Intention and Affinity scores](https://app.gitbook.com/s/XSPACE_SETUP/plan-and-integrate/set-up-advanced-features/affinity-and-intention-ml-algorithm#stories-ready-made-intention-and-affinity-scores)                              |
| Story, score and rank       | [Stories Intention: stories, scores and ranks](https://app.gitbook.com/s/XSPACE_SETUP/plan-and-integrate/set-up-advanced-features/affinity-and-intention-ml-algorithm#stories-intention-stories-scores-and-ranks)                                         |
| Hidden affinity             | [Stories Affinity: persistent interest, including hidden interest](https://app.gitbook.com/s/XSPACE_SETUP/plan-and-integrate/set-up-advanced-features/affinity-and-intention-ml-algorithm#stories-affinity-persistent-interest-including-hidden-interest) |

## Which score answers your question

<table data-search="false"><thead><tr><th width="330">Your question</th><th>Score to build on</th></tr></thead><tbody><tr><td>Who is about to buy in this category?</td><td><strong>Intention</strong>. It only exists while a purchasing cycle is open.</td></tr><tr><td>Which category should this user's next message be about?</td><td><strong>Intention</strong>, taking the rank 1 story.</td></tr><tr><td>Who is interested in this category, whether or not they are shopping right now?</td><td><strong>Affinity</strong>. It is a long-term view and does not expire with a cycle.</td></tr><tr><td>Who might be interested in a category nobody browses much?</td><td><strong>Affinity</strong>, which can score a category a user has never interacted with.</td></tr><tr><td>How large is the audience with a strong interest in this category?</td><td><strong>Affinity</strong>, filtered on the High score.</td></tr></tbody></table>

## Build the segment

{% stepper %}
{% step %}

### Confirm the scope you have

A score exists only for the product scopes and channels agreed with your Customer Success Manager. A category outside that scope has no score at all, which is not the same as having no interested users.
{% endstep %}

{% step %}

### Pick the score and the intensity

Both scores carry three intensity levels - **High**, **Medium**, **Low**. Choose the one that matches the pressure you intend to apply: High for a conversion-driven message, Medium or Low when the point is to keep a user engaged.
{% endstep %}

{% step %}

### For Intention, decide the rank you act on

A user can hold up to 10 simultaneous stories, ranked by purchase probability. Targeting **rank 1** only sends each user the message closest to conversion and keeps marketing pressure down. Widening to ranks 1 to 3 raises reach and dilutes relevance.
{% endstep %}

{% step %}

### Combine with your own criteria

A score is one criterion among others. Two combinations are worth building deliberately:

* **Intention, excluding cart abandoners.** Cart abandoners are usually already activated by a dedicated trigger campaign. Excluding them leaves the incremental audience: users with strong purchase signals who have not put anything in a basket yet.
* **Affinity, excluding recent buyers of the same category**, when the point of the campaign is discovery rather than repeat purchase.
  {% endstep %}

{% step %}

### Save, and let the segment compute

The segment behaves like any other: it is populated at the next computation and updated from then on. See [Compute your audience from stored data](/audience-and-activation/build-your-audiences/target-your-audience-based-on-criteria/compute-your-audience-from-stored-data.md).
{% endstep %}
{% endstepper %}

## Match the message to the score

For Intention, the score tells you what kind of message the user is ready for:

<table data-search="false"><thead><tr><th width="160">Score</th><th>Activation strategy</th></tr></thead><tbody><tr><td><strong>High</strong></td><td>Direct conversion: retargeting, promotional offer.</td></tr><tr><td><strong>Medium</strong></td><td>Mid-funnel engagement: product exploration push, cart nudge.</td></tr><tr><td><strong>Low</strong></td><td>Re-engagement: bring the user back to the site, maintain attention.</td></tr></tbody></table>

For Affinity, the score decides **what** the message is about rather than how hard it pushes: use the highest-scoring category to choose the products, the offer, or the block of content a user sees.

{% hint style="info" %}
**Urgency-based personalisation.** Prioritise the users closest to conversion across every channel at once - email, paid media, on-site personalisation - each of them receiving the message matched to their stage. The same segment can feed several destinations: see [Send your first-party data to a destination](/audience-and-activation/activate-your-audiences/send-your-audience-to-a-destination/send-your-first-party-data-to-a-destination.md).
{% endhint %}

## Verification

* The segment computes to a plausible population, and the count moves between updates. Both scores are recalculated in real time, so a static count is a signal that something upstream is stalled.
* Two segments built on different intensity levels of the same category do not return the same users.

## Troubleshooting

<table data-search="false"><thead><tr><th width="300">Symptom</th><th>What it means</th></tr></thead><tbody><tr><td>No score is available in the builder at all</td><td>Stories is not enabled on your account, or the scope has not been configured yet. Contact your Customer Success Manager.</td></tr><tr><td>A category you sell has no score</td><td>It is outside the configured product scope, or the events for it do not carry the required properties.</td></tr><tr><td>A user has an Affinity score for a category they never visited</td><td>Expected, and useful. Affinity infers interest by correlation across your whole user base.</td></tr><tr><td>The audience is too small for the destination you had in mind</td><td>Widen the intensity levels, or the Intention ranks, before considering a different score. Check the destination's own minimum audience size in the <code>Connectors</code> section.</td></tr></tbody></table>

## Related pages

<table data-view="cards" data-search="false"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Define your audience based on criteria</strong></td><td>Building a segment from criteria, in a builder or in OTQL.</td><td><a href="/audience-and-activation/build-your-audiences/target-your-audience-based-on-criteria.md">Define your audience based on criteria</a></td></tr><tr><td><strong>Expand your audience with Lookalike</strong></td><td>The other way to reach users you have not identified yourself.</td><td><a href="/audience-and-activation/build-your-audiences/expand-your-audience-with-lookalike.md">Expand your audience with Lookalike</a></td></tr><tr><td><strong>Segment builders</strong></td><td>The three tools the scores are available in.</td><td><a href="/audience-and-activation/build-your-audiences/segment-reference/segment-builders.md">Segment builders</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.mediarithmics.io/audience-and-activation/build-your-audiences/target-users-by-affinity-and-intention.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.