Skip to main content


Optimizely Knowledge Base

Build interest-based audiences with adaptive audiences

This article will help you:
  • Build and configure an adaptive audience.
  • Create tags, or modify existing tags for use with an adaptive audience.

Optimizely’s adaptive audiences let you target visitors based on their interests. Instead of relying on extensive data analysis to define explicit behavioral targeting rules, you can create a predicted intent audience condition that captures a certain percentage of your visitors who are most interested in a specific topic. Optimizely uses machine learning to figure out on its own whether or not they belong in your new audience.

Adaptive audiences currently only support English-language websites.

Predicted intent audience conditions also estimate the audience’s reach—or the number of visitors that could potentially be included—over the next seven days.

You build and use an adaptive audience the same way you would build any Optimizely audience: via the audience builder. 

But before you build an adaptive audience, you will first have to set up tags. The tags should capture the main idea of this page’s content, such as a title or description. Optimizely creates an interest score by matching keywords to each tag. This interest score is based on the pages a visitor has viewed on the site, such as articles or product pages. As a visitor browses content on these tracking pages, Optimizely evaluates how strong that visitor’s interest is in the topics you specified when creating the audience, and any visitor whose interest meets or exceeds the level you specify is included in the audience.

Set up tags

To set up tags, follow the steps below:

If you’ve already configured tags for adaptive audiences, skip ahead to the next section.

If you've already set up tags in the past for other purposes, skip ahead to step 5 below for each tag you want to include, to ensure they can be used with an adaptive audience.

Screen Shot 2019-02-26 at 10.43.48 AM.png

To set up a tag, follow these steps:

  1. Navigate to Implementations -> Pages. 

  2. Create a new page, or select an existing one.

  3. In the Visual Editor, click on Visual Tags in the menu on the left-hand side.

  4. Select the appropriate string value type.

  5. Check the checkbox labeled Capture text for visitor intent prediction.

  6. Type the tag name into the text box and click Save.

Build an adaptive audience


  1. Name your new audience.

  2. From the Conditions section of the audience builder, select Predicted Intent and drag it to the audience conditions box on the left.

Screenshot 2019-02-26 at 10.23.08 AM.png

  1. In the keywords field, add the tags you're most interested in for this audience. You can include up to 12 separate tags. Valid keywords will be displayed in blue text, while invalid keywords are red.

Screen Shot 2019-02-26 at 10.29.06 AM.png

It can take up to 24 hours for a new adaptive audience to process. 

Once the audience has finished processing, you'll see the Interest Group graph in the audience condition itself. This graph provides basic metrics on reach.

  1. Specify the percentage of your most-interested visitors who are included in the audience.


Screen Shot 2019-02-26 at 10.26.20 AM.png

You can also use the slider in the graph to set the percentage of your most-interested visitors who are included in the audience. When Optimizely recalculates which visitors qualify for your adaptive audience (which happens once per day), that percentage will remain the same. However, the corresponding interest score may change. For example, if your visitors as a whole are suddenly showing more interest in your keywords, and the percentage is set at 25, the interest score required to be included in that top 25 percent will go up.

Keep in mind that you'll have to wait for the audience to process before you can use the slider.

Predicted intent can be combined with other audience conditions. When you do this, those other audience conditions are not affected by the percentage of most-interested users specified in your predicted intent audience condition.