You can create Remote Config parameters that have different values depending on a user's predicted behavior.
- On the Predictions page, find the prediction you want to use, and then click Explore and use prediction.
Define the user segment you want to target with your campaign, then click Next.
A user segment is made up of the users that fall inside a range of percentile values, which you specify. A user's percentile value represents the relative likelihood of the user performing an action (churn, spend, and so on), compared to all users. Each user's percentile value is assigned by sorting your users according to their likelihood of performing the predicted action and then splitting the sorted list into 100 equal-sized groups.
For example, when predicting spending, a user in the 25th percentile is as likely or more likely to spend than 25% of your users, and users in the segment containing percentiles 1-25 are the 25% of your users least likely to spend.
Firebase Predictions predefines the following user segments:
Least likely The 25% of users least likely to perform the action (percentiles 1-25). Middle The middle 50% of users (percentiles 26-75). This segment often represents your most convinceable users. Most likely The 25% of users most likely to perform the action (percentiles 76-100).
If you want to target a percentile range other than one of the presets, you can define a custom user segment by specifying your own upper and lower bounds. In the Firebase console, the lower bound of the range is exclusive and the upper bound inclusive, so the ranges 0-50 and 50-100 don't overlap.
Select Remote Config and click Continue. The parameter creation interface opens, with the Target section pre-filled with the user segment you selected.
Specify the name of the parameter you want to set and the value the parameter will have for users in the Target segment.