Collaborative Algorithms

In Collaborative Algorithms, product recommendations are based on what similar users have engaged previously taking product visits, purchases and added-to-carts into account. This algorithm finds similar users to the current user and recommends products from similar users that are not visited by the current user. It is suitable for e-commerce, OTA and event websites and can be used on Home Page to widen the opportunity of new discoveries by presenting items that users would not have looked for. 

The algorithm covered under Collaborative Filtering is User-based Recommendation.

User-based

In this algorithm, product recommendations are based on the behavior of similar users (users with close similarity index scores: viewed, purchased, or added the same or similar category products to their cart) with the current user. The algorithm recommends products that similar users came across in the past but not visited by the current user. The user-based algorithm also takes the user-product-rating matrix as another input. For each product visited by a user, a rating is calculated based on the number of visits, purchases, and add-to carts within the last 30 days. In short, it recommends products that these akin users have engaged with previously but haven't been explored by the present user.

• Page Type: All types of pages
  Your title goes here

  The algorithm does not consider the similarity of products such as category or brand. Thus, you can use it on all pages, but it’s not recommended to use it on the category and/or product pages since the recommendations can come from non-relevant to the categories.
• Example Use Case: Opportunity for new discoveries by presenting items that users would not have looked for on the Homepage.
• Fallbacks: Viewed together, Most popular items, Most popular items of the category
• Prerequisites: Users' view, add to cart, and purchase data collected for 30 days
• Maximum Number of Products to Recommend (in the same campaign):  15