Criteria
- Topics:
- Recommendations
Criteria in Adobe Target Recommendations are rules that determine which products or content to recommend based on a predetermined set of visitor behaviors. Criteria can be based on popular trends, a visitor’s current and past behaviors, or similar products and content. You can test multiple recommendation types against each other by adding multiple criteria.
The following sections explain more about the criteria keys and the recommendation logic that you can use for each key. Click the links for more detailed information.
Industry Vertical
While creating a criteria, you select an industry vertical based on the goals of your recommendations activity.
| Industry Vertical | Goal |
|---|---|
| Retail/Ecommerce | Conversion resulting in purchase |
| Lead Generation/B2B/Financial Services | Conversion with no purchase |
| Media/Publishing | Engagement |
Other criteria options change based on the industry vertical you select. You can set your default industry vertical on the Administration > Recommendations page or you can specify the industry vertical for each criteria.
Algorithm Type
The algorithm type that you select determines the available algorithms.
The following table explains the various algorithm types and their accompanying algorithms.
| Algorithm type | When to use | Available algorithms |
|---|---|---|
| Cart-Based | Make recommendations based on the user’s cart contents. |
For more information, see Cart-Based in Base the recommendation on a recommendation key. |
| Popularity-Based | Make recommendations based on the overall popularity of an item across your site or based on the popularity of items within a user’s favorite or most-viewed category, brand, genre, and so forth. |
|
| Item-Based | Make recommendations based on finding similar items to an item that the user is currently viewing or has recently viewed. |
|
| User-Based | Make recommendations based on the user’s behavior. |
|
| Custom Criteria | Make recommendations based on a custom file that you upload. |
|
For more information about each algorithm, see Base the recommendation on a recommendation key.
Using a custom recommendation key
You can also base recommendations on the value of a custom profile attribute.
NOTEFor example, suppose that you want to display recommended movies based on the movie that a user most recently added to the queue.
-
Click Recommendations > Criteria.
-
Click Create Criteria > Create Criteria.
-
Fill in the information in the Basic Information section.
-
In the Recommended Algorithm section, select Item Based from the Algorithm Type list.
-
Select People Who Viewed This, Viewed That from the Algorithm list.
-
Select your custom profile attribute from the Recommendation Key list (for example, Last Show Added to Watchlist).
Viewing criteria information
You can view criteria details by clicking the desired criteria in the Name column.
The Attributes and Details sections let you view general information about the selected criteria, including its Name, Description, Industry Vertical, Page Types, Recommendation Key, Recommendation Logic, Algorithm ID, and Last Modified information (date and who modified the algorithm).
The Usage section lets you view a list of activities that reference the selected criteria.
NOTE