Recommendations

In this tutorial, you'll learn how to enable product recommendations as well as how to implement recommendations in your email creative how to use merge tags to dynamically inject product recommendations into your HTML templates. 

In This Article

Recommendations Brief

Recommendations are made up of the top selling products across your entire catalogue as defined by your customers' purchase behavior. Our recommendation algorithm predicts what products your customers will want to buy next and intelligently serves these items in your email campaigns.

We've made it very easy to recommend products based on browse activity and cart data to help you increase your CTR and revenue per email.

Below are some examples of product recommendations in email campaigns. To learn more about how to strategize your recommendations  click here.

 

Recommendation Settings

We've made it very simple to manage your recommendations in the application. It's important to know that in order to start using product recommendations, you must first make sure that these are enabled in your account's Settings. 

Enabling or Disabling Recommendations

1

To see your recommendation settings you will need to go to your account settings and then click on the Recommendations link at the top.

2

Next, you'll need to use the toggle to enable or disable the use of recommendations. 

If the toggle is green, your recommendations are enabled and you're ready to start using them

If the toggle is red, your recommendations are disabled and no data is being collected.

Once you've enabled your recommendations, the application will start collecting user data, all while learning about the most popular items to recommend. 

When you enable your recommendations, you'll notice two other settings: 

  • Aggregation timeline: this setting allows you to manage the timeframe which the app should consider in order to define your catalogue's top sellers.
  • Products to Exclude: this setting is useful for suppressing items that you do not want to recommend.

Aggregation Timeframe

This setting helps us determine the timeframe you'd like to use for your product recommendations. The default is "All Time" where we look at your all time top sellers.

You are able to change this setting to a more fitting timeframe depending on your business type and product catalog. So for example, if you would like your top sellers recommendations to reflect ONLY the last month, you should select the timeframe of "Last month" to make sure that we're injecting the overall top sellers of the last 30 days.

After making your selection you will need to save your recommendation settings by pressing the green button at the bottom.

Products to Exclude

You can suppress certain items that you do not wish to feature in your recommendations. 

1

Go into the "Products to Exclude" section of your Recommendation Settings. 

2

Inside the input simply start by typing the product ID (SKU) you wish to suppress. A list of available items under the ID or product name you type will populate to help you make a selection. You can either select from the list or add a product to the suppression list by typing the product ID, or the product name. Note that you list population is case sensitive.

The product ID and product name of the items you suppress will be visible in your "Excluded Products" list. You can always click on the x next to the product name in order to remove from the suppression list.

Note: The product exclusion feature will only auto-populate for products that have been converted. Meaning that we will not recommend low-sale items to your customers.
3

Once your suppression list is ready, you'll need to save your recommendation settings. Otherwise, you will lose your exclusion settings.

 

Recommendation Types

We define recommendation types as the product “taxonomy” we want the recommendations to follow. Below is a listing of the types available, their definition, and their type usage.

RECOMMENDATION TYPE DATASET TYPE USAGE
Products Viewed Together *
Other items that customers have also browsed based on a customer's browsing session.
* Requires v4 Implementation
viewed_together
Browsed Category Top Sellers *
Top selling items based on the categories of products viewed during a customer's browsing session.
* Requires v4 Implementation
browsed_category_top_sellers
Category Top Sellers
Category top sellers based on the items in a customer's cart / order.
category_top_sellers
Overall Top Sellers
Top selling items from your entire product catalogue.
top_sellers
Products Frequently Purchased Together
Frequently purchased items based on the items in a customer's cart / order .
purchased_together

 

Merge Tag Attributes

Tag attributes are those that relate directly to the product’s makeup/content. These attributes are part of the recommendations merge tags that will determine what you’d like to inject into your template.

Attributes available for ALL recommendations:

ATTRIBUTE DESCRIPTION TAG USAGE
Name Name of the product name
Product URL The URL to the product's page product_url
Image URL The URL of the product's image image_url
Category The product's category category

Attributes ONLY available for Category Top Sellers, Overall Top Sellers and Products Frequently Purchased Together:

ATTRIBUTE DESCRIPTION TAG USAGE
Price The price of the product price|cents_to_dollars
Note: You can append UTM parameters and promotional codes at the end of a product_url like so:
{{products.purchased_together.0.product_url|append_query:'promo=rjr123'}}
{{products.purchased_together.0.product_url|append_query:'?utm_source=rejoiner&utm_medium=abandonment&utm_campaign=email01'}}

 

Usage

Strict Injection Method

In order to establish a rigid structure, you need to know the number of items you want to inject. Then, you will start counting your items from ZERO. Next, you'll add the order of the product within the structure of your recommendation tags – which you can see below.

Simple example of a recommendation tag:

{{products.category_top_sellers.0.name}}

Again, the listing of recommended products starts with ZERO, so you can use the logic below to further structure your recommendations. 

  • The FIRST product’s listing is = 0

    {{products.category_top_sellers.0.name}
    	
  • The 2ND product listing is = 1

    {{products.category_top_sellers.1.name}}
    	
  • The 3RD product listing is = 2

    {{products.category_top_sellers.2.name}}
    	
  • The 4TH product listing is = 3

    {{products.category_top_sellers.3.name}}
    	

Etcetera

Usage and Process

1
To beging coding, we must (first) use an if statement with the correct tag type and  index of  product. In this case, the recommendation type we'll use as an example is for Products Frequently Purchased Together:

{% if products.purchased_together.0 %}
	
View all recommendation types here
2
Next, we want to add the merge tags / product information we want to show. We'll start by injecting the  image:

<img style=”max-width: 104px; border: none;” src=”{{products.purchased_together.0.image_url}}” alt=”{{products.purchased_together.0.name}}” />
	
Note: You will want to make sure that we add a maximum width to these images.We also want to add the product name in the alt=” ” property.
3
Next, we want to add the name below the image:

{{products.purchased_together.0.name}}
	
4
Next, we want to hot-link the image and the product name to the product page like so:

<a href=”{{products.purchased_together.0.product_url}}” target=”_blank”>LINK TEXT HERE</a>
	
5
Lastly, we want to close the if statement using the tag below:

{% endif %}<br>
	

As we're implementing a rigid structure, you'll want to repeat the steps above for every item you want to inject. 

So if you want to inject 4 items, you'll repeat these steps four times. For an example of the end-result of this process, see below:

EXAMPLE **

** This example is just for demonstration purposes, not a template.

Fail-Safe Scenarios

Though our application's recommendation algorithm will match other product recommendations to a product there will be times where we can't generate a match. These are edge cases such as when the item to match is a new addition to your product catalogue. We recommend to implement a fail-safe via a conditional regardless of the method you use to structure your recommendations.

This is due to the fact that you may add special styling or an introductory text to your recommendations. So if we cannot generate a match, you will be left with a row of text in your email that shows no products. Thus, leaving a bad impression.

So for example, if you were to recommend Products Frequently Purchased Together and your customer added a new product in your catalogue to their cart. There's a chance this new product may no trigger any recommendations. Therefore, the best scenario is to substitute the   purchased_together recommendations section with top_sellers

You can easily do this via a conditional that states that IF there are matches for X recommendation taxonomy, show these, ELSE replace recommendations with Z taxonomy. 

Note that fail-safe usage is only applicable when recommendations are using the following taxonomies: 
  • Products Viewed Together
  • Browsed Category Top Sellers
  • Products Frequently Purchased Together
  • Category Top Sellers
Note: It is highly unlikely – if not impossible – that Rejoiner won't generate recommendations for your Overall Top Sellers. 
For that reason, we tend to recommend using this type as your fail-safe.

Below you will find steps to create a fail-safe conditional that will automatically switch the recommendation taxonomy in order to guarantee that your recommendations section is bullet-proof.

In this case, we're going to substitute category_top_sellers items with top_sellers if there are no matches.

1
If there are no purchased_together items to match 
{% if products.purchased_together %}
<!-- CATEGORY TOP SELLERS RECOMMENDATIONS HTML --><br>
	
2
THEN replace with top_sellers 
{% else %}
<!-- TOP SELLERS RECOMMENDATIONS HTML --><br>
	
3
End conditional. 
{% endif %}
	

At the end you will end up with something like this:

Note: You must make sure that each section uses the correct structure as delineated by the Strict Injection Method steps above.

Another option is to completely hide the whole recommendations section if there are no matches. 

To do this you will just need to add the first part of the conditional statement and the closing tag to end the statement so that it reads like:

1
If there are no category top sellers to match – hide the section 
{% if products.category_top_sellers %}<br>
	
2
End conditional: 
{% endif %}
	

To help you we've generated the fail-safe conditionals snippets below for every recommendation type:

<!-- Products Viewed Together -->

<!-- start conditional -->
{% if products.viewed_together %}
<!-- section HTML --> {% endif %}
<!-- end conditional --> 

<!-- end section -->
<!-- Browsed Category Top Sellers -->

<!-- start conditional -->
{% if products.browsed_category_top_sellers %}
<!-- section HTML --> {% endif %}
<!-- end conditional -->

<!-- end section -->
<!-- Category Top Sellers -->

<!-- start conditional --
{% if products.category_top_sellers %}
<!-- section HTML -->
{% endif %}
<!-- end conditional -->

<!-- end section -->
<!-- Products Purchased Together -->

<!-- start conditional -->
{% if products.purchased_together %}
<!-- section HTML -->
{% endif %}
<!-- end conditional -->

<!-- end section -->

Exclude Injected Items

Exclude filters are powerful builtins part of the Rejoiner templating language. You will only be needing an exclusion filter when implementing several injection types at once. Thus, if you are planning to inject product recommendations along cart or browsed data, we recommend using exclusions in order to avoid duplicates.   Learn how to use exclusion filters here.

Still need help? Contact Us Contact Us