Email with top products

Sometimes your customers are not sure what they are looking for. Help them to decide by sending the best-selling items - promote them further in your communication. When people see the bestseller label on your product, they’ll feel more inclined to buy it over another items offering in the same category. It is called “purchase pressure.” Some buyers go straight to the bestseller list to see what is popular now.

You can promote your bestsellers among your customers. You can dynamically add to this email all bestsellers from all categories or just from specific category, often visited by customers.

Examples of use - Retail industry


A client from the retail industry prepared a -20% summer sale for the entire collection. This client have sent an email with information about the discount to half of the customers. The second half received an email with a discount and several best-selling items. The email with bestsellers had better results.

Screenshot presenting email with summer sale 20
Email with -20% summer sale


  • 2,3% CTR for email with bestsellers
  • 1,8% CTR for email only with discount


To be able to implement this use case, you must:

How to do it

To create an email with top products, perform the steps in the following order:

  1. Configure AI recommendations.
  2. Prepare an email with top products.
  3. Configure an email communication.

Configure AI recommendations

Important: If you do not have AI models trained yet, follow this instructionto import product feed to Synerise.

To be able to recommend items from the top category in various communication types, first you need to initiate the model training for the item feed from which you want to recommend your items.

  1. Go to Settings > AI Engine Configuration > Add feed.
  2. Select the type of the feed.
    Tip: We recommend using Google Merchant feed due to the size limits for XML files imported to catalogs.
  3. After you add the feed, it’s added to the list.
  4. Double-click the feed on the list of feeds.
  5. In the Recommendation models section, select top products.
    Screenshot presenting model of recommendation
    Top products in recommendation module
  6. For the rest of the settings, follow the procedure here.

Prepare an email with top products

Prepare a recommendation message that offers best-selling items, which you will later use in the email template.

  1. First you have to prepare recommendations message and add new recommendation.
  2. Select the catalog on which your recommendation will be built.
  3. Then choose Top products in recommendation type to be trained according to Top items model.
    Screenshot presenting type of recommendation
    Top items in recommendation type
  4. In the Items section, define the type of items to be included in the recommendation by using filters.
    Tip: You can check the instruction for the recommendation filters and explore examples of use.
    1. You must choose Minimum and Maximum number of items which the recommendation frame includes.`
    2. Use elastic and static filters to select items to your recommendation frame.
    3. In the Additional settings section, you have to influence the arrangement of items in the recommendation. More information is available here.
      Items section requires you to define more details about your recommendation. Obligatory choose **Min.** and **Max.**  number of products which user has to get, and in **Sorting** define metric which has to be used to find products to the message.
  5. After saving the recommendation, get the ID of the message.
    Screenshot presenting site with list of campaign
    List of email recommendation

Configure an email communication

In this use case, configure an email communication that will reuse the content of the recommendation you created in the previous step. While configuring the email, you must select a group of customers, create the content of the email and set up the final setting.

1. Select the audience of the email message

Select the customers who will get the email with the top selling items.

  1. Choose the customers in segmentation or create a new segment directly in the email message.
  2. Choose users who will get email.
Screenshot with define audience mode
Define the audience

2. Create content

After selecting the email recipients, create content.

  1. Select the email account from which the email will be sent.

  2. Prepare the subject of the email.

  3. Click Create message and built the template of your email. To include the top item recommendations, use the following Jinjava code and your own CSS. Let’s look at how to prepare the appropriate jijnava code.

    Check the Jinjava code

       <!-- Opening the tag that retrieves the value from one recommendation prepared in point 1--> {% recommendations3 campaignId=xxx %} for loop below: <!-- In the section {% for r in recommended_products3 %} a {% endfor %} there is access to all variables from a given object (products here) - which parameters you add to the template depends on you. --> {% for r in recommended_products3 %} <!-- {{ r.itemId }} {{ r.title }} {{ r.imageLink }}{{r.price.value}}{{r.salePrice.value}} - parameters taken from the recommendation. The itemId is a standard name, but others (like category, price, salePrice, title, imageLink) only depend on names defined in the feed--> {{r.itemId}} {{r.title}} {{r.imageLink}} {{r.price.value}} {{r.salePrice.value}} {% endfor %} <!-- Closing of the tag that gets the value from the recommendation prepared in point 1 --> {% endrecommendations3 %} 

  4. Optionally, add the B variant of the template which will not contain the top product.

3. Prepare the final settings

  1. Add the title of the email.
  2. In the Schedule tab, decide when your email is sent.
  3. In the UTM & URL parameters section, add the parameters to track the email performance.
  4. Send tests of your message to verify if the content of the email is displayed correctly.
Screenshot with final setings
Set up settings page
Important: Test message can only be sent when it has a title.

Read more

This use case belongs to the following categories:




We are sorry to hear that

Thank you for helping improve out documentation. If you need help or have any questions, please consider contacting support.



Thank you for helping improve out documentation. If you need help or have any questions, please consider contacting support.