Reviewing Suggested Queries by Coveo Machine Learning

The Coveo™ Machine Learning (Coveo ML) Query Suggestions feature proposes the most relevant similar queries that were performed previously (see Query Suggestions Feature).

To prevent one user or infrequent queries to pollute the suggestions, the feature delivers suggestions only for queries meeting the following minimal requirements:

  • Query performed at least 10 times by different users or in different sessions.

  • At least 5 of the query occurrences are followed by a click (end-user clicking a search result).

Before enabling Coveo Machine Learning Query suggestions, you may wonder which queries logged by usage analytics from a given search interface would be candidates for query suggestions, basically ensuring that there are queries matching the minimum requirements. This verification is particularly useful when your search interface has low traffic, such as in the case of a search interface exclusively accessible to employees in a small company.

You can use the Analytics section of the administration console navigation menu to list queries that match the Query Suggestions minimal requirements (see Who Can Perform the Page Actions). You can then establish whether the feature can have a significant impact on a specific search interface for a specific language.

The following procedure takes into account that you are familiar with global dimension filters and dashboards (see Adding Global Dimension Filters and Reviewing and Managing Dashboards).