Einstein Personalization Recipes brings advanced, per-user product and content suggestions using complex algorithms and a deep understanding of user behavior. The solution offers configurable "recipes" that can be used to boost content or product discovery on your site. Recipes consist of ingredients, exclusions, and boosters, which can be constructed in a variety of combinations to serve up the right content or products based on the individual visitor's behavior and affinities on your site. These recipes are then queried against the Einstein Personalization engine and the individual query results are presented to each visitor as his or her personalized recommendations.
This article will give an overview of adding recommendations by creating a recipe, testing a trained recipe, editing existing recipes, and deleting recipes. Refer to related articles for information on adding ingredients, exclusions, and boosters.
Testing and Publishing a Trained Recipe
Once the recipe is complete and trained, you should test it before publishing.
- Refer to Test an Einstein Recipe for detailed instructions on testing a recipe
- Make adjustments to the recipe as needed to produce the desired recommendations. Depending on your selections, you may need to click RETRAIN when finished
- Click PUBLISH to make the recommendations recipe available for use in campaigns