Session-Based Product Recommendations

In this article

Coveo Machine Learning (Coveo ML) Session-based product recommendations models take advantage of the user profile and commerce usage analytics events to suggest relevant products based on current user interactions with a Coveo-powered commerce implementation.

Unlike traditional Product Recommendations (PR) models, which usually suggest products to end users based on cooccurrences machine learning methods, Session-based product recommendations models rely on product embeddings and session vectors to determine which products to recommend.

Since Session-Based Product Recommendations (SBPR) models leverage the History of Actions user profile dimension, the recommendations provided are updated in real time, meaning the algorithm continuously processes the actions taken by the user to recommend products that are relevant to their current shopping session. This is also useful in scenarios where users aren’t authenticated as the algorithm can infer the user’s intentions as soon as they start interacting with the interface.


During a shopping session on a Coveo-powered sporting goods commerce interface, an unauthenticated user performs the following actions:

  1. Enters Golf iron sets in the search box.

  2. Navigates through the iron sets that are being displayed on the results page, and then clicks on mid-range golf iron sets.

  3. Enters Golf driver in the search box, navigates through the available drivers, and then returns to the home page.

By analyzing the user’s session, the model understands that they’re currently looking for mid-range golf equipment. Therefore, since the recommendations interface on the home page leverages a Session-based product recommendations model, the products that are being displayed to the current user are complementary products, such as mid-range golf gloves and balls.


Session-based product recommendations models require the History of Actions user profile dimension to be enabled on the Coveo organization, Contact us to activate this feature.


To use Session-based product recommendations, you must comply with the following prerequisites: