Target groups are specific user segments used by actions to define a recommendation set-up.

Target groups overview

Clicking on the Target groups header on the left side menu enables you to view all of the active target groups and their relevant actions. Clicking on the “+” sign in the Target group header will create a new target group.

Below the Target group header is a list of the individual target groups. Clicking on the “+” sign next to a specific Target group on the left side menu allows you to create a new action for the given Target group. Next to the “+” is a trash icon that allows the user to delete that target group.

The Target group detailed page can be accessed by either clicking on an individual target group shown in the left side menu or by clicking on the pencil icon shown in each listing on the main page.

There is always one target group by default called “Everybody”. This is a special item as it cannot be deleted or modified.


Editing a Target group

A target group is a combination of attributes that are selected by the user. 

There are two “+” signs below “And” and the “Or”. Clicking on the “+” below the “And” sign allows the user to narrow down the group of selected users. Clicking on the “+” below the “Or” sign allows the user to extend the group of selected users.


Available attributes for a Target group

Traffic Source

When selecting an attribute for a Target group, there is a drop-down menu after clicking a “+” sign. One of the key attributes in this list is “traffic source” that allows you to select from where visitors are coming from. Once “traffic source” has been selected, you have two options. The first is to create a keyword that relates to where visitors are coming from. For example, it makes sense to type in “bicycle” if you are interested in finding people who have been searching for bicycles. Another option is to use “campaign” that relates to a specific campaign ID number. This is designed to display relevant content for a user after they click on a specific advertisement on a third-party page. 

For example, imagine if you own a travel site and you publish a banner on a third party site about a trip to Barcelona. The visitor clicks on the banner shown on a news portal and is then taken to your travel site. Now, on the landing page shows the visitor more information about the trip and the opportunity to immediately book the trip.

User Events

Another option after clicking on the “+” sign is “User Events”. Clicking on  “User Events” allows you to select users based on their past behavior or history. Clicking on the drop-down menu enables you to select one of these four options: Buy, View, Add to Cart, and Any. For example, selecting “Buy” will display all of the people whoever bought something on a particular site. Selecting “Any” will display all of the people who have previously visited the site.

There are four check boxes called “Filter for item”, "Timing",  “Filter for event property”, and "Number limit". Clicking on the “Filter for item” box allows you to create a more detailed filter. Using the drop-down menus, one can narrow down the range of site visitors. For example, select price below “Item Property” and then “greater” below “Match type”. Now type in a value below “Item Property Value” to complete the equation. This now means that you are filtering for everyone who has ever bought an item of $1,000 or more. Click on the “Add” button to make this filter become active.

Under "Timing" you are able to filter for a certain time period, for example, users, who bought something in the last two days.

Clicking on the “Filter for event property” box enables you to define a period of time during which certain actions occur. For example, you can select the users who bought an item during the past five days. It is also possible to select the users who bought something more than a month ago.

Under "Number limit" you can further narrow down your target group by setting a minimum (and maximum) number of events from the specified kind - for instance, users, who opened 3 or more product pages in the last 10 minutes.

Last Visit

This feature also allows you to select users based on their browsing history. For example, you can create a filter for users who visited the site within a certain timeframe or select the ones who have not visited your site during a given period.

User Data

This feature is quite useful when a CRM system is connected to the recommendation engine, or if you have "Login tracking" enabled under "Settings -> Installation" that pairs the cookie Ids of your visitors with email addresses they've entered on your site. Clicking on the dropdown will display all of the filters available.

Request Parameter

Clicking on the dropdown reveals a detailed list of parameters. These parameters are specified during integration. For example, if you would like to deliver different content to different countries, then you can select the “country code” parameter and define a user group based on that.

A/B Test Basic

This is a simple way to create an A/B test, which allows you to test new campaign logic against an existing one. An A/B test can provide useful and rapid insight into the impact changing a variable has on an existing campaign.

First, click on a “+” sign and it will reveal a drop-down menu. Using this menu, select “A/B Test basic” and you will see the words “user is in group” next to a green box. In the field next to this text, please select either “A” or “B”. Users are randomly sorted into either the “A” or “B” groups. 

Clicking on the “+” signs below next “And” and “Or” allows you to narrow down or extend the user selection.

A/B Test Advanced

The difference between A/B Test Basic and A/B Test Advanced is two things:

  1. A/B Test Advanced allows you to change the name of the test to whatever you want.
  2. The whole user base is segmented into 100 different pieces. The A/B Test Advanced allows you to determine what percentage will be allocated to which part. For example, moving the blue slider to 30 means that 30% will be in the “A” group and 70% will be in the “B” group.