Firebase Predictions predefines two user segments that are dynamically generated and continuously updated based on your analytics data.
Churn predictions
The churn segment contains users who have been active in the last day but are predicted to stop using your app in the next 7 days. Note that churn is different from uninstalling your app. Users may churn long before they uninstall an app. However, Predictions uses app uninstalls as one of the signals to train its model.
Spend predictions
The spend prediction contains users who are likely to make in-app purchases
(that is, users expected to log the
in_app_purchase event).
These are users who, behaviorally, look like past spenders.
Users in the lower percentiles of the spend prediction are unlikely to make
in-app purchases. You can use this information to experiment with different
monetization strategies, like for example, showing ads only to users unlikely to
spend.