In this article
We walk you through the steps of creating a modeled cohort to expand your audience.
Once you click “Create”, it will take around 12 hours to train the model. However, it might occasionally take longer than that. Once the model has been trained, you will see a curve like the one below in the dashboard. This curve allows you to understand the expected reach for each point along the confidence scale.
The confidence measures how sure the model is about a given prediction. While the reach of a classification model is the entire audience, the model will be less certain about some users than others. For this reason, you use the confidence threshold to restrict your model to only classify users it is more certain about.
To create a modeled cohort:
- Move the slider to select a minimum confidence threshold
- Then click on one of the “Dataset classes” buttons.
- This will bring up a model like the one below, asking for confirmation to create a modeled cohort.
Note: You can create multiple modeled cohorts from the same model - with different combinations of seed labels and minimum confidence scores.
Once you create the modeled cohort, you will find it on the “Modeled Cohorts” page. Here you can also enable the Google Ad Manager integration.
Comments
0 comments
Article is closed for comments.