Introduction

The Item Attributes recommendation model allows you to create rule-based recommendations by applying catalog item attribute filters. This allows you to customize recommendations based on your marketing goals, whether promoting specific items or providing personalized suggestions based on user profiles.

Generic Rules

Generic rules use item attributes and are not personalized. They promote new arrivals, seasonal items, and specific brand or category promotions to many users. By leveraging item attributes, businesses align recommendations with marketing objectives and increase visibility.

Example Use Cases

• Reveal the 'New arrivals' section.
• Inspire with your branded collection.
• Celebrate with our festive picks.

Targeted Rules

Targeted rules filter item attributes based on user profiles to deliver tailored suggestions aligned with each user's characteristics. This ensures relevant recommendations suitable for specific user profiles.

Example Use Cases

• Recommend ideal jobs matched to users' skills
• Locate the local restaurants near your customers.

Geo-location Rules

Geo-location rules help provide location-specific recommendations. These rules can be used to suggest items or services that are available near the user's current location or a custom-defined location.

Example Use Cases

• Suggest nearby restaurants, stores, or services based on the user's current location.
• Suggest nearby listed properties based on the user's current location.

Filters

The filter settings allow you to refine the recommendations shown to your customers. These filters work alongside the item attribute model rule to enhance the relevance of the suggested items.

You can filter items in two ways:

• Keep Items: This filter allows you to define user action criteria that will include only those items that are common in both the results of item attribute rules and user action filter criteria.
• Remove Items: This filter allows you to define user action criteria that will remove items from the results of item attribute rules.

Example use cases

• Recommend items from the Ethnic wear category, but remove those that the individual users have added to their cart in the past 7 days.
• Recommend Flash Deals items, but keep only those items that the individual users have added to their wishlist in the past 14 days.
• Recommend properties in the user's location, but remove those that the user has visited in the past 30 days.
• Recommend movies, but exclude those that the user has watched in the past 30 days.

Creating Item Attribute Recommendations

1. Go to Content > Recommendations from the left navigation. The Recommendations page is displayed.
2. Click Create Recommendation. The Create recommendation page is displayed.
3. Select the Item attributes model and click Next.

4. In the Recommendation name field, enter a name for the recommendation.

5. In the Recommendation description field, enter a description for the recommendation.

6. In the Catalog drop-down list, select the relevant catalog from which you wish to retrieve these recommendations.
7. Now, you can set up either generic rules or targeted rules.
   • To create a generic rule, choose the relevant item attribute in the Item where drop-down list and choose the Custom Value option.
   • To create a targeted rule, choose the relevant item attribute in the Item where drop-down list and select the User Property option.
     Note: Ensure that the defined item attribute(s) and user attribute(s) carry a similar type of information.
     
   • You can also create a combination of generic and targeted rules.
8. Turn the Filter items by user actions toggle on to add filtering criteria and control which items to recommend to their customers. These filters are applied to the results of the core recommendation further. You will see two types of filters for user actions:
   
   

   • Select user action to keep items: Marketers can define the user action criteria that includes only those items that are common in filtering user action criteria and recommendation results. Click + User actions and select the items to be included.

   • Select user action to remove items: Marketers can define the user action criteria that removes the items according to the filtering user action criteria from recommendation items. Click + User actions and select the items to be excluded.
9. In the Sort the filtered items section, sort the recommendation results by any numeric attribute. For example, price.
10. Click Save. The recommendations listing is created with an 'Active' state on the recommendations listing page.