Commerce models
Commerce models
Several Coveo Machine Learning (Coveo ML) models are designed specifically for commerce use cases. These models are covered in the Machine learning for Commerce section.
In addition to the commerce-specific models listed below, some platform models such as ART, QS, and DNE also have commerce-specific variants. See the Machine learning for Commerce section for details.
|
Note
A model can take anywhere from several minutes to several hours to build, depending on the size of the model dataset and the number of model build requests in the queue (system load). |
Commerce-specific models
-
Leverage user interactions and analytics to suggest relevant products based on end-user profiles, contexts, and buying behaviors.
-
Session-Based Product Recommendations (SBPR):
Use real-time user interactions to deliver personalized product recommendations.
-
Predictive Query Suggestions (PQS):
Provide relevant query completion suggestions tailored to commerce search patterns.
-
Intent-Aware Product Ranking (IAPR):
Rank products on search result pages based on the visitor’s shopping intent.
-
Rerank products on search result pages by learning from aggregate visitor behavior.
-
Enhance product ranking on Coveo-powered product listing pages (PLPs).
-
Catalog Semantic Encoder (CSE):
Enhance product discovery in commerce search interfaces using semantic understanding.
-
Combine catalog text and product images to improve product discovery for descriptive queries.
-
Conversational Product Discovery:
Blend natural language conversation with product search to guide shoppers from exploratory intent to purchase-ready selections.