The AddSearch Recommendations tool identifies and recommends sets of products or documents which are frequently purchased or viewed together. For example, users can be recommended related news articles or items which are often combined in purchases.

Visualization for recommendations.

The Recommendations feature uses the Fp-growth algorithm. This is a frequent-pattern mining algorithm used for finding frequent items in a dataset. It uses a tree-based data structure called the frequent pattern tree (FP-tree) to efficiently discover frequent itemsets.

To use the Recommendations tool, a dataset will need to be added via the AddSearch dashboard or pushed using the Indexing API. Once this data has been provided, configurations can be created.

Implementing Recommendations require usage of AddSearch API or JavaScript libraries:

Was this helpful?

Need more help?

We’re always happy to help with code or other questions you might have. Search our documentation, contact support, or connect with our sales team.