Firebase Predictionsplat_iosplat_androidplat_cppplat_unity

Firebase Predictions applies machine learning to your analytics data to create dynamic user groups based on your users' predicted behavior. These predictions are automatically available for use with Firebase Remote Config, the Notifications composer, and A/B testing.

When you use Predictions with Remote Config, you can increase conversions by providing a custom experience based on each of your users' predicted behavior.

You can use Predictions with the Notifications composer to deliver the right message to the right user groups.

And, with A/B testing, you can evaluate the effectiveness of your prediction-based strategies.

Get Started

Key capabilities

Bring the power of Google's machine learning to your data Firebase Predictions applies Google's expertise in machine learning to your analytics data, creating dynamic user groups based on users' predicted behavior. With Google's powerful machine learning, you can make product decisions based on predicted behavior, rather than historic behavior.
Boost conversions through dynamic, customized user experiences Firebase Predictions is integrated with Remote Config, letting you customize a user's experience based on their predicted behavior. For example, for users who are predicted to spend, you can show a new in-app purchase bundle, while for users who are predicted to not spend, you can adjust the frequency of ads. Groups update dynamically over time as an individual's prediction changes, so you can always offer a fresh, personalized experience to your users.
Increase retention with smarter notifications Re-engaging a user who has already stopped using your app is tough. By using Predictions, you can engage users who are predicted to churn, before they ever stop using your app.
Create custom predictions In addition to the built-in predictions—will churn, will not churn, will spend, and will not spend—Firebase Predictions allows you to create predictions based on any conversion event in your analytics data. Once you define the event, Predictions creates a dynamic user group composed of users who are predicted to complete that event in your app.

How does it work?

Predictions are available for iOS and Android apps that include the Analytics SDK. Predictions creates dynamic groups of users who are likely to complete a certain event over the next 7 days. You can use these groups to target users with Remote Config and the Notifications composer.

By default, Predictions provides two types of predictions: churn, which predicts which users will disengage from your app over the next 7 days (that is, they will not open the app or app-related notification messages), and spend, which predicts which users will spend money in your app over the next seven days. You can also create your own predictions based on custom conversion Analytics events that you collect in your app.

Predictions lets you adjust the risk tolerance of a prediction so that you can strike the right balance between targeting fewer users with more accuracy, or more users with less accuracy, and it shows you what percentage of your user base will be targeted at each risk tolerance level. The machine learning model for your app improves as the amount and relevance of data collected using Analytics increases, and as your number of users increases. In addition, the accuracy of the model for a specific user will improve further after that user has used the app for at least a few days.

Predictions creates groups of users, called predicted user groups. You can send notifications to the predicted user groups. Or, you can change the behavior or appearance of app instances used by predicted user groups using Remote Config.

Do I need to share my data with Google in order to use Firebase Predictions?

Firebase Predictions is trained on your app's data, You need to use Google Analytics for Firebase to log your app data to Firebase. You also need to make sure your analytics data is shared with Predictions (see Enable Analytics data sharing and Predictions in your app). You are not required to share your analytics data with Google to use Predictions.

Implementation path

Add Analytics to your app To make predictions, your app needs to record conversion events using Google Analytics for Firebase.
Enable Predictions and monitor prediction readiness Use the Firebase console to start making predictions based on your app's analytics data and to monitor whether predictions has enough data for the built-in churn and spend predictions. You can also use the Firebase console to monitor whether enough Analytics data is available for predictions that you create based on additional Analytics events collected by your app.
Act on predictions using Remote Config, the Notifications composer, or both

When you have enough data for a prediction, you can target users in your predicted user group at various risk tolerance levels.

For example, you could use the churn prediction with high risk tolerance to send notification messages to users who might churn. Or, you could use the churn prediction with a low risk tolerance to make changes to the appearance and behavior of your app for only those users who you are highly confident will churn.

Next steps

Send feedback about...

Need help? Visit our support page.