Introduction

Content recommendations are crucial in driving user engagement and watch time for marketers of OTT platforms. By understanding user preferences through their viewing history, ratings, and interactions, you can generate content recommendations that align with their interests. You must display these recommendations in the most relevant and opportune moments, ensuring that users are more likely to engage with the suggested content.

Advantages of recommending content to watch next

• For Users:
  • Discovery: Recommendations help users find content they might not have otherwise discovered, expanding their viewing horizons and potentially leading to new favorites.
  • Convenience: Personalized recommendations save users time and effort by suggesting content that aligns with their tastes, making it easier to choose what to watch.
  • Increased engagement: Platforms encourage users to watch more by suggesting relevant content, leading to increased engagement.
  • Reduced churn: Keeping users engaged and satisfied with their viewing experience can help reduce churn.
• For Platforms:
  • Content promotion: Recommending popular or new content can help drive viewership and promote the platform's library.
  • Monetization: Increased engagement and viewership can translate to higher advertising revenue or subscription retention.
  • Personalized experience: Platforms can create a more personalized and satisfying viewing experience by tailoring recommendations to individual users.

In this article,  we will achieve this use case in two steps:

• Create a recommendation
• Create a Push Campaign 

Expected Result

Users receive a push notification with recommendations of what to watch next on their phones: 

 

Step 1: Create a Recommendation

In this section, let us create a recommendation based on the user actions.

1. On the left navigation menu in the MoEngage dashboard, click Content and then click Recommendations. For more information, refer to Creating User Action Recommendations.
2. On the Recommendations page, click + Create recommendation. You are taken to the first step, Select recommendation model.
3. Under Predictive, click the Similar items card because it considers the user's action of watching content and related information in attributes such as the genre, director, and cast. This model uses Merlin AI to predict what other content the same user would prefer.
4. Click Next. You are taken to the second step, Create recommendation.
5. Enter the following details:
   1. Recommendation name: Enter a name for the recommendation. For example, WhatNextToWatch. This will be the name through which you will refer to the output of this recommendation model.
   2. Recommendation description: Enter a description for the recommendation. This description helps you to understand the model's aim.
   3. Catalog: Select the catalog to which the recommendation is to be applied. In this example, we will select Recommendations Demo Catalog.
      
6. Under Generate recommendations based on the most recent, select Custom user action. In the Item where user performed list, select Product Viewed.
7. Click Create to save the changes and run the model.
   
   The model is expected to be ready in 24 hours. You can find the status of the model on the Recommendations home page:
   
   The recommendation engine shares the set of content a user might prefer based on the list of content they watched in the last 10 days.

Now that we have created the recommendation, let us create a Push campaign to nudge people about the content that they have viewed but not completed.

Step 2: Create a Push Campaign

In this section, we will create a Push campaign to recommend what to watch next to your users.

Step 2.1: Target Users

1. Navigate to the MoEngage dashboard sidebar on the left and click Engage > Campaigns and click + Create campaign or click + Create new > Campaign.

2. Under Outbound, select Push > Periodic.

   

   You are taken to the first step, Target users, in defining your campaign. 

3. Define your campaign with a name and tags. 
4. In the Target audience section, select Filter users by.
5. On the User behavior tab, select users who have not watched content in the last 1 day.
   
6. In the Target Platforms section, select Android.
   
7. Click Next.

You will move to the second step, Content, to define the content for your Push campaign.

Step 2.2: Content

1. Select the template that you would like to use. For our example, select Basic notification.
   
2. Enter the required content for the campaign. We can manually enter a title, message, and summary or generate it using Merlin AI. For more information, refer to Generate Push Messages with Merlin AI. 
3. While defining the message, select the product set generated through the recommendation you defined.
   1. Enter “@.” The Push Personalization dialog box appears.
   2. Search for WhatNextToWatch, which is the name of the recommendation you built. 
      
   3. Click Done. 
      The following JINJA code is inserted in the Message field:
      

   4. Edit the code to run a loop through each content and list down the first suggestion because the highly confident suggestions come first from the Recommendation engine. The higher the confidence, the higher the content will be in the list. The final JINJA code looks as follows:

      JINJA

          {% if ProductSet.WhatNextToWatch%}
      
          {% for product in ProductSet.WhatNextToWatch[0:1]%}
      
          {{product.title}}
      
          {% endfor %}
      
          {% else %}
      
          MOE_NOT_SEND
      
          {% endif %}

      In line 2, the loop does only one iteration using “[0:1]” in the query. If you want to suggest the top 3, you can change the same to “[0:3]” and so on. The {{product.product_name}} element in line 3 prints the name of the suggested content. For more information, refer to Jinja Templating Language.

   5. Enter the following code to get the image of the recommended watch:

      JINJA

          {% if ProductSet.WhatNextToWatch%}
      
          {% for product in ProductSet.WhatNextToWatch[0:1]%}
      
          {{product.image_url}}
      
          {% endfor %}
      
          {% else %}
      
          MOE_NOT_SEND
      
          {% endif %}

      In Line 3, {{product.image_url}} provides the link to the image of the concerned title of the suggested content.

4. Add a deep link to the push notification, mentioning the URL that will directly take users to your app's mentioned title or suggestion list. This reduces the possibility of a user dropping off before finding the suggested content.
   
5. Click Next to move to the third step, Schedule and goals, where you can define your campaign's schedule and goals.

Step 2.3: Schedule and Goals

1. In the Send campaign section, define when you want to start and end your campaign.
   
2. Change the deliverability settings based on your requirements. For more information, refer to Create Push Campaigns.
3. Click Publish.

Conclusion

In this use case, we created a recommendation on what to watch next and sent it to users through push notifications.

All MoEngage AI products, which were previously referred to as Sherpa AI, are now known as Merlin AI.