About Query Suggestions (QS)

This is for:

Developer System Administrator

Query suggestions example | Coveo Machine Learning

Coveo Machine Learning (Coveo ML) Query Suggestion (QS) models recommend relevant queries to users as they type in the search box.

Coveo ML QS models:

  • Identify exact, partial, or fuzzy matches with typed characters anywhere in any individual keyword appearing in any order.

  • stem query suggestion keywords to remove duplicates.

  • Offer the most relevant recommendations by ranking query suggestions by considering the following:

    • The number of times the query was performed.

    • The degree to which the query suggestion matches the typed characters.

    • The query performance based on the Relevance Index and Clickthrough usage analytics metrics.

  • Only consider queries that were followed by clicked search results a specific number of times (see Review query suggestion candidates). This prevents infrequent queries from polluting the suggestions.

  • Automatically adjust recommendations based on user topics, tailoring query suggestions according to each user’s main topic of interest. This personalization enhances the relevance and effectiveness of search results by aligning them with individual user profiles.

Note

To ensure optimal performance, a QS model limits the number of possible suggestions per language to a preset maximum. The limit is enforced after the most relevant query suggestions are identified and ranked, and after any manually defined default query suggestions are applied. The enforced limit is large enough to not negatively impact the quality of the suggestions. The most relevant suggestions are always recommended to the user, regardless of the enforced limit. The limit, however, may explain why a query that appears as a candidate in your data isn’t suggested for a given user query.

Members with the required privileges can configure and activate Coveo ML QS in a few clicks. Developers can leverage QS in the desired search interface using the JavaScript Framework, the Headless library, or with Atomic.