Manage Machine Learning Models

Coveo Machine Learning (Coveo ML) models are algorithms which leverage usage analytics data to provide contextually relevant recommendations (see Coveo Machine Learning models).

The Models (platform-eu | platform-au) page of the Coveo Administration Console allows users with the required privileges to manage and review the ML models of a Coveo organization.

Creating a model

Each Coveo ML model type has its own set of prerequisites and a different model creation procedure. Click one of the following links to access the corresponding procedure:

Creating a model with JSON

Click one of the following links to access the corresponding procedure:

Editing a model


"Status" column

On the Models (platform-eu | platform-au) page of the Administration Console, the Status column indicates the current state of your Coveo ML models.

When inspecting the Status column, a given model is either in the Active or Inactive state. Additional information can be displayed depending on the model’s current state.

status column

The following table lists the possible model statuses, their definitions, and their status colors as shown in the Administration Console:

Status Definition Status color


The model is active and available.



The model isn’t available.


Update in queue

Waiting to process a scheduled update or configuration change.



The model is being rebuilt based on a new configuration.



The model is in the building queue.



The model is currently being processed.



The model is active, but has some limitations. Additional information is available in the Error section of a model (see Review Coveo Machine Learning model information).



The model couldn’t be built with the requested configuration. Additional information is available in the Error section of a model (see Review Coveo Machine Learning model information).


Update failed

The model couldn’t be updated with the requested configuration.



An error prevented the model from being built successfully.



The model was archived because it hasn’t been queried for at least 30 days.
Learn more on archived models.


"Learning Interval" section

In this section, you can modify the following:

  • Frequency: The rate at which the model is retrained.

  • Data period: The usage analytics data time interval on which the model will be based.

The more data is available for the model to learn from, the better will be the recommendations. As a general guide, a usage analytics data set of 10,000 queries or more typically allows a Coveo ML model to provide very relevant recommendations. You can look at your Coveo Usage Analytics (Coveo UA) data to evaluate the volume of queries on your search hub, and ensure that your Coveo ML models are configured with a training Data Period that corresponds to at least 10,000 queries. When your search hub serves a very high volume of queries, you can consider reducing the data period so that the model learns only more recent user behavior and be more responsive to trends.

A Coveo ML model is regularly retrained on a more recent Coveo UA data set, to ensure that recent user behavior is learned and that the model freshness maintained.

Set your Coveo ML model training Frequency parameter in relation with the Data Period value. Select a longer time interval for a larger Data Period and a shorter time interval for a smaller Data Period as recommended (√) in the following table.

Data Period





1 month



3 months (Recommended)


6 months


  • Because very frequently retraining a model based on a long period would have very little effect and consume significant Coveo ML service resources, some Data Period and training Frequency parameter value combinations aren’t allowed.

  • If your Coveo organization has not yet collected enough data according to requirements, but your search interface has more than 55 visits per day in which a user query is followed by a click for a specific language, you can reproduce the following configuration depending on when you start collecting data:

    Data collected for Data Period Frequency
    Daily Weekly Monthly
    1 to 29 days 1 month check
    1 month 3 months check

"Learn From" section

The Learn From section allows you to refine the data that the model uses to make its recommendations. By narrowing down the set of data that a model uses, you can better customize relevancy for specific user groups and use cases. You can apply filters on all events, or on every event that belongs to a specific category (i.e., search, click, view, or custom events).

  • You want your QS model to return queries that pertain to a specific user group, so you add a data filter to ensure that only a specific set of analytics are used by the model for training purposes.

  • Your Community search and Agent search have very specific vocabulary. You don’t want them to influence one another in the ART model learning process, so you add a filter on the Origin 1 (Page/Hub) dimension.

To add a filter:

  1. Depending on whether you are creating or editing a model:

    • When creating a model, click Add-Filter

    • When editing a model, in the Learn from section:

  2. In the Select a dimension drop-down menu, select the dimension on which you want to base the learning of the model.

  3. In the Select an operator drop-down menu, select the appropriate operator.

  4. In the Select value(s) drop-down menu, add, type, or select the appropriate value.

  5. Click Add Filter.

Required privileges

By default, members of the Administrators and Relevance Managers built-in groups can view and edit elements of the Models (platform-eu | platform-au) page.

The following table indicates the privileges required to use elements of the Models page and associated panels (see Manage privileges and Privilege reference).

Action Service - Domain Required access level

View models

Machine Learning - Models
Organization - Organization
Search - Query pipelines


Edit models

Organization - Organization
Search - Query pipelines


Machine Learning - Models