Recommendations Features

The widgets are easy to configure and provides an intuitive way of answering a shopper’s perceived need.

Broadly, our recommendations solutions are categorized into:

• Collaborative filtering: Collaborative filtering systems produce user-specific recommendations of items based on patterns of ratings or usage (e.g. purchase) without need for exogenous information about items or users.
  For instance:
  • Bought Also Bought
  • Viewed Also Viewed
• Content-Based Filtering: Content-based recommenders make recommendations by matching a description of an item (a general term for any kind of content or information, e.g. a book, video, or event) and a profile of the shopper’s interests.
  For instance:
  • Cross-Sell
  • More Like This
• Sales-based analytics: Recommendations based on revenue earned for a specific product/category/retailer/geography for a specific period of time.
  For instance:
  • Top Sellers (Home Page)
  • Category Top Sellers (Category Page)
  • Brand Top Sellers (Product Brand Page)
  • Product Top Sellers (Product Display Page)
• Personalized: User behavior is used to create user profiles that contain information about individual shopper preferences. Products are recommended based on aggregated user behavior information.
  For instance:
  • Recommended For You
  • Recently Viewed
• Hybrid Recommendation systems: Where both content-based and collaborative recommendation systems are used to provide product recommendations that are based on the behaviour of the specific user and group of similar users. 
• Editorial filtering: Recommendations based on business decisions that merchandisers and product managers set for specific products/categories. 
  • Complete The Look

Each of our widget allows merchandisers and product managers make powerful business decisions using AI algorithms.

While recommendations are proven to drive revenue, we help you analyze what kind of products are more likely to be accepted and converted into a successful order when recommended, thus resulting in higher AOV and understand what kind of recommendations won’t work, thereby increasing shopper retention.