About Predictive Query Suggestions

In addition to recommending relevant queries to users when they type in the search box, Coveo Machine Learning Predictive Query Suggestions (PQS) models add an additional layer of personalization to the offerings of Query Suggestions (QS).

The “predictive” aspect provides an additional result boost based on Product Embeddings and Vectors personalized to the user’s session when performing queries. In other words, it predicts the next query the user would have performed in the search box, and suggests it in real time, meaning that PQS also personalizes the experience for anonymous users.

Coveo ML PQS models:

  • Increase conversion by reducing friction in the shopper journey.

  • Increase search usage.

  • Increase clicks on suggestions.

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


Predictive Query Suggestions must be enabled to provide end users with relevant query completion suggestions. Contact us to enable this model type.