Reduce the amount of events required to build a model

Coveo Machine Learning (Coveo ML) models learn from usage analytics data. If fewer than 100 usage analytics events are available for your model, recommendations can’t be provided just yet.

Members with the required privileges can activate the Test configuration mode for a model when very few analytics are available to train a model.

To provide relevant output, Coveo ML models filter out the following by default:

  • Infrequent queries

  • Queries that were not followed by sufficient clicks

  • User context keys that were not seen frequently enough

  • Browsing patterns that were not performed frequently enough

When the test configuration mode is activated, the model reduces the amount of analytics data it needs to provide recommendations. This is ideal to test a model in a sandbox environment.


In a non-production organization (sandbox), you create a model for testing purposes. Since you don’t want to generate a hundred events and want the model to provide recommendations immediately, you activate the test configuration mode for this model.

To activate the test configuration mode

  1. On the Models (platform-ca | platform-eu | platform-au) page, click the model for which you want to add advanced parameters, and then, in the Action bar, click Edit.

  2. On the subpage that opens, select the Advanced tab.

  3. At the upper-left corner, select the advanced configuration parameter that you want to configure for this model. Available parameters differ depending on the type of model you want to configure. Select below the type of model for which you want to configure advanced parameters for instructions about the available advanced parameters: