Diversify media recommendations
If you want to ensure that media recommendations results returned from a singlerecommendation request are more diversified rather than looking similar, you canturn on diversification. This feature is available only for mediarecommendations, not custom search and recommendations.
Generally, diversification reduces the likelihood that similar content isshown in a recommendation panel, at the risk of removing some goodrecommendations.
Diversification is set on the serving config level. You can have multipleserving configs per media recommendations app, each with a differentdiversification setting. For more about serving configs, seeCreate and manage media serving configs.
Two types of diversification are available: rule-based diversity and data-drivendiversity.
Rule-based diversity
Rule-based diversity relies on the categories that are uploaded with yourcontent. Use rule-based diversity to recommend content from a variety ofcategories. Diversification is configured by level, with higher levels ofdiversification causing fewer items to be displayed per category. Thisdiversification type works best if your content has high-quality categories.
| Diversification level | Maximum items per category |
|---|---|
| None | Unlimited |
| Low | 3 |
| Medium | 2 |
| High | 1 |
| Auto | Depends on content |
In general, setting rule-based diversity and using filter recommendations is notadvised. For more information, seeFilters and diversificationsettings.
Data-driven diversity
Use data-driven diversity to produce recommendation results that balancerelevance and diversity. Data-driven diversity learns from content metadata suchas titles or categories. Instead of relying on words from a title or category,data-driven diversity uses semantic similarity to produce better-performingdiversification.
| Diversification level | Maximum similar items |
|---|---|
| None | Unlimited |
| Low | 3 |
| Medium | 2 |
| High | 1 |
| Auto | Depends on content |
Diversify recommendations
To diversify your media recommendations:
In the Google Cloud console, go to theAI Applications page.
Click the name of the app that you want to configure recommendations for.
Go to theConfigurations >Control tab.
If you have more than one serving config, select the serving config that youplan to set diversification for.
In theResult diversification section, choose how to diversify yourrecommendations in theDiversification type field.
Turn on theEnable diversification level toggle to see theavailable diversification levels.
Select a diversification level for your recommendations.
ClickSave and publish.
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-02-19 UTC.