# C. Data-driven attribution model

> In addition to our data-driven attribution models, we also offer **classical ones**: first click, last click, linear etc.

Adloop data-driven attribution model is based on users' behaviour. We use all the micro-conversions available in your Analytics source, like key pageviews (product or category), click on a CTA, add to basket and so on.

The **more micro-conversions** you are tracking, the **more detailled our data-driven model** will be! So don't hesitate to track new actions on your website.

Then, for each micro-conversion, you have to indicate to Adloop **how engaging this action** is on the path to conversion. For that, we use commitment levels, from very low to very high.

By default we scale:

* the *pageview* as very low commitment, as viewing a page is the most basic action you can do on a website
* the *new users* as very high commitment, as it gives value to the upper-funnel channels bringing in new users

Some examples of scaling that could help you when setting up the data-driven attribution model:

* *view of a product page*: low commitment
* *view of a category page*: low commitment
* *displaying the details of a product*: medium commitment
* *add to wishlist*: high commitment
* *add to basket*: very high commitment
* *subscribe to newsletter*: very high commitment
* *store locator*: medium commitment
* *demo booking*: very high commitment

Those are just few examples, as every website is different, you are the best to judge how engaging the actions on your website are.

> If you don't know which micro-conversions to use, just navigate on your website and put yourself in the shoes of a potential customer discovering your website for the first time and then purchasing!

We scale differently the different steps of the conversion funnel: delivery choice, delivery address, contact information, payment choice. Those are not to be included in the commitment scaling step.

Our algorithm will take into account the scaling of the micro-conversions when calculating attribution.

**The more a user interacts with the website on a touchpoint, the more credit this touchpoint will get when calculating the attribution and contribution.** This touchpoint will get a bigger fraction of the conversion and of the revenue.

![](https://github.com/CommandersAct/Adloop-Documentation/blob/master/.gitbook/image-2014969896.png?width=680)

## Attribution set up

![](https://github.com/CommandersAct/Adloop-Documentation/blob/master/)


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://community.commandersact.com/adloop/vii-adloop-tracking-and-attribution/c.-data-driven-attribution-model.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.