Page tree
Skip to end of metadata
Go to start of metadata


New Name: Marketing Cloud Personalization

Interaction Studio (formerly Evergage) is now known as Marketing Cloud Personalization. The new name reflects our mission and vision for innovation in Salesforce Marketing Cloud. We wish we could snap our fingers to update the name everywhere, but you can expect to see the previous name in various places until we replace it.

Recommendations can be challenging to troubleshoot. This article outlines a three-step process for troubleshooting an Einstein Recipe, however, if at any point you need extra help during this process, please reach out to the Support team for assistance.

This Article Explains

This article details the steps to troubleshoot issues with Einstein Recipes.

Sections in this Article

Step 1 - Examine the Recipe

The first step in troubleshooting your recipe is to take a closer look at how it was constructed. If the results don’t match your expectations, verify that the ingredients, exclusions, and boosters were added as intended. The maximum number of items that a web template can return is 12, however, your developer can configure a template to return fewer than 12 items. If the recipe isn’t returning any results, there are several things to check:

  1. What ingredients were used to build the recipe? If the recipe was built with an ingredient requiring an “on page” anchor item, or point of reference, which includes Co-Buy, Co-Browse, SmartBundle, and Similar Items, you also need to enter a sample item name or ID as the anchor item for the recipe to be able to return results. As you enter different item names or IDs into the Viewing field, you’ll see that the recipe returns different results based what the visitor is viewing on the page at that moment.

  2. Is the anchor item returning results? If the recipe was built with an ingredient that requires any anchor item - in cart, on page, or last purchased - it’s possible that the recipe training didn’t generate the requisite data for that anchor item. For example, if you trained a Co-Buy ingredient, there may not be enough other items bought by the visitors that bought the current anchor item. If the ingredient in use requires an "in-cart" or "last purchased" anchor item, find a visitor that has an open cart or recently purchased an item. If the recipe doesn’t already include a backup ingredient, try adding either Trending or Collaborative Filtering as a fallback ingredient. Then, retrain the recipe, and preview it again to see if the recipe returns results.

  3. Is there an Exclusion in the recipe? Exclusions always override inclusions, so If there is a conflict, the exclusion will always win. Check for conflicting inclusions and exclusions that could result in the recipe not returning any results.  

  4. Is the expected item promotable? Certain items will not show unless all criteria is met. All items must not have their promotion state set to Excluded. If there is a published date, the current date must be after that time. If there is an expiration date, the current date needs to be before that time. Each product must have a value for the following item attributes: ID, name, URL, image URL, and a price greater than zero. Any product inventory counts must be greater than zero.

Step 2 - Examine Unified Customer Profile

Once you’ve confirmed that the recipe was built correctly and the returned recommendations still don’t make sense, investigate the unified customer profile of the visitor you are using to preview recommendations returned by the recipe. It can be insightful to look at his or her affinities and data at a more granular level. You can review this information to help determine if the results actually make sense based on the individual visitor’s data.

  1. Open another browser tab and log into Interaction Studio 
  2. Double click a visitor listed on either the Recent Visitors report (Reports > Recent Visitors), User Segments > All Users, or the Users tab of a segment 
  3. Research this visitor’s affinities by views, view time, and purchases, as well as information about visits, purchases, and action details
    1. Boosting by Category - you can verify whether the recipe results make sense based on the visitor’s category affinities
    2. Boosting by Tag - you can see if the results agree with the affinities for the visitor’s brand, gender, style, author, or other preferences
  4. Repeat this process for as many different visitors as needed to help you understand the results returned

Step 3 - Methodically Test the Recipe

If you’ve researched the Unified Customer Profile for different visitors and are still not satisfied with the returned results, begin methodically testing the recipe:

  1. Remove all ingredients, exclusions, and boosters

  2. Add one recipe component at a time

  3. Retrain the recipe, if prompted (required after removing or adding ingredients)
  4. Preview results to uncover the component most responsible for the results you are seeing