Recommendation offers a wide range of algorithms and filters suitable for various use cases.
Algorithm
Algorithms determine which items to recommend (such as the most popular items, items the user viewed in the past, and so on).
Filters
Additional filters you can apply based on product properties:
Only include: Recommend only products with a specific property (for example, items that cost more than $30).
Exclude: Never recommend products with a specific property (For example, never recommend items that are on sale).
Pin: Recommend only a specific product (For example, brand is Zara).
Algorithms
Name | Description |
Best-selling | The Best-Selling Products Algorithm identifies and displays products with the highest number of purchases over a specified period. It ensures that users can quickly access trending and high-demand items based on real sales data. |
Newest | Displays most recent products added to the catalog. |
Most popular | Scores items based on the weighted sum of all interactions – such as purchases, add to cart, and product view – favoring recent interactions over historical ones. |
Viewed Together | Recommend items that have been viewed in the same session as the item currently displayed. |
Purchased Together | Recommends products that have been purchased together with the item currently displayed. It scores items based on the number of times they have been purchased together in the same transaction while demoting products that are typically purchased with many other items. Consequently, it recommends products that are strongly linked to one another rather than products that have an arbitrary connection to a popular product. |
Recently viewed | Recommends the last items viewed by the current user (most recent appears first). |
Viewed with Recently Viewed | Items that are usually viewed in the same session as the last items viewed by the current user. |
Recently purchased | The last items purchased by the current user (most recent appears first). |
Purchased with Recently Purchased | Items that are usually purchased together with the last items purchased by the current user. |
Category affinity | Focuses on recommending items within categories that the user has shown interest in. The algorithm tracks user interactions within specific categories and prioritizes recommendations within those categories. |
Product affinity | Recommends items based on the user's affinity for specific products or types of products. This is determined by analyzing the user's past interactions with similar items and focusing on those product characteristics. |
Image Similarity | Identify and recommend items that are visually similar to the item currently displayed, matching things that the user can’t describe and that the marketers didn't tag into the metadata. |
Product Similarity | Recommends items that are similar to the item currently displayed, factoring in item popularity. |
Similarity | A blended strategy to show products which are similar based on multiple algos. |
Collaborative filtering | Items viewed, purchased, or added to the cart by users similar to the current user. |
User Affinity | Personalized for each individual user and scores items based on derived user preference and item popularity. |
Fallback logic for product recommendations
When the algorithm returns fewer products than required, a fallback mechanism ensures a seamless user experience by filling the gaps with alternative recommendations.
For example, User Affinity for users with no past behavior, or Viewed Together for items that were never viewed with other items in the same session. For these cases, this is the fallback logic.
Algorithm | Fallback | Fallback |
Category Affinity → | Viewed with Recently Viewed → | Most popular |
Product Affinity → | Viewed with Recently Viewed → | Most popular |
Keyword Similarity → | Viewed with Recently Viewed → | Most popular |
Purchased Together → | Viewed Together → | Most popular |
Viewed Together → | Most popular |
|
Viewed with Recently Viewed → | Viewed Together → | Most popular |
Purchased with Recently Purchased → | Purchased Together → | Most popular |
The following algorithms have no fallback: Recently Viewed and Recently Purchased
Recommendation Filters
When setting your recommendation strategy you can add dynamic filtering to customize the algorithm. These filters are based on inclusion/exclusion/pin rules in addition to the algorithm chosen.
Name | Description |
Include | Only products that meet predefined conditions based on product attributes will be included in the product feed |
Exclude | Only products that do not meet predefined conditions based on their attributes will be excluded from the product feed. |
Pin | Specific products are pinned to the top based on predefined conditions related to their attributes. |
Recommendation using an API Call
You can use an API to retrieve product recommendations from Intempt and add them to your system. This allows you to display recommended products in your application, website, or any platform where you want to show personalized suggestions.
Response Format
The API returns the recommended products in JSON format.
Embed Code (Snippet)
Copy and edit the API snippet to customize the output as needed.
Adding Fields
The fields feature allows you to define which product attributes to display.
Use the "Add variable" button to include fields or remove them using the (X) icon.
This ensures product cards display only the most relevant information.
Parameters:
id: The feed ID used for recommendations.
quantity: The number of recommended items to return (default is 5).
fields: The product attributes to include in the response (default: title, image URL, and price).
Note: The product ID is required for recommendation cases, including:
Viewed together
Purchased together
Image similarity
Product similarity
Similarity
Collaborative filtering
In Shopify, Magento the product ID is added automatically.
In IOS SDK, Android SDK, Node JS SDK, users must manually add the product ID.