--- title: Announcing Firebase Predictions Beta | daily.dev description: Firebase Predictions has launched in beta, bringing Google's machine learning to Firebase developers by building dynamic user groups based on predicted... canonical: https://daily.dev/posts/announcing-firebase-predictions-beta-zvznmpptw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Announcing Firebase Predictions Beta | daily.dev og:description: Firebase Predictions has launched in beta, bringing Google's machine learning to Firebase developers by building dynamic user groups based on predicted... og:url: https://daily.dev/posts/announcing-firebase-predictions-beta-zvznmpptw og:image: https://api.daily.dev/og/posts/zvzNmppTw.png og:image:alt: Announcing Firebase Predictions Beta og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Announcing Firebase Predictions Beta **[Firebase](https://daily.dev/sources/firebase-blog)** · 4 min read · 0 upvotes · 0 comments ## Summary Firebase Predictions has launched in beta, bringing Google's machine learning to Firebase developers by building dynamic user groups based on predicted behavior. Four built-in groups are provided out of the box: Churn, Not_Churn, Spend, and Not_Spend, updated daily. Developers can adjust a tolerance slider to balance population size against false-positive risk, and target predicted groups using Remote Config or Firebase Cloud Messaging notifications. Custom predictions can also be created based on custom app events, allowing targeting of users likely to trigger a specific conversion event. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Firebase Predictions and what does it do? Firebase Predictions is a beta product that uses Google's machine learning to build dynamic user groups based on predicted future behavior, updated daily. It ships with four built-in groups: Churn, Not_Churn, Spend, and Not_Spend, each predicting behavior over the next 7 days, and these groups can be targeted with Firebase Cloud Messaging notifications or Remote Config. _daily.dev keeps developers building predictive engagement features current on new Firebase capabilities._ ### How does the tolerance slider work in Firebase Predictions? The tolerance slider lets developers choose low, medium, or high risk of false positives when defining a predicted user group. A low tolerance yields a smaller population with fewer false positives, while a high tolerance yields a larger population but more users incorrectly included, such as a 'churn' prediction targeting someone who actually keeps using the app. _Developers tuning behavioral targeting trade-offs can track product updates like this via daily.dev._ ### Can I create custom predictions in Firebase beyond the built-in churn and spend groups? Yes, custom predictions can be created based on custom events set up in an app, such as a level_up event in a game. Once saved, a prediction card populates over time in the Firebase Console just like the built-in Churn, Spend, and Not_Spend groups, and it can be used the same way to target notifications or Remote Config values. _Teams building custom engagement logic can follow Firebase feature updates on daily.dev._ --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#mobile](https://daily.dev/tags/mobile), [#firebase](https://daily.dev/tags/firebase) [View this post on daily.dev](https://daily.dev/posts/announcing-firebase-predictions-beta-zvznmpptw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Announcing Firebase Predictions Beta","url":"https://daily.dev/posts/announcing-firebase-predictions-beta-zvznmpptw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/announcing-firebase-predictions-beta-zvznmpptw"},"datePublished":"2026-08-23T12:20:07.110Z","dateModified":"2026-08-23T12:31:45.660Z","description":"Firebase Predictions has launched in beta, bringing Google's machine learning to Firebase developers by building dynamic user groups based on predicted...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7ed721de96163685d26ab7e314be3ebc?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7ed721de96163685d26ab7e314be3ebc?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Firebase","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Firebase","logo":"https://media.daily.dev/image/upload/s--i395oqZH--/f_auto,q_auto/v1787487448/logos/firebase-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/firebase-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/announcing-firebase-predictions-beta-zvznmpptw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,mobile,firebase","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Firebase","item":"https://daily.dev/sources/firebase-blog"},{"@type":"ListItem","position":3,"name":"Announcing Firebase Predictions Beta"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/announcing-firebase-predictions-beta-zvznmpptw#faq","mainEntity":[{"@type":"Question","name":"What is Firebase Predictions and what does it do?","acceptedAnswer":{"@type":"Answer","text":"Firebase Predictions is a beta product that uses Google's machine learning to build dynamic user groups based on predicted future behavior, updated daily. It ships with four built-in groups: Churn, Not_Churn, Spend, and Not_Spend, each predicting behavior over the next 7 days, and these groups can be targeted with Firebase Cloud Messaging notifications or Remote Config. daily.dev keeps developers building predictive engagement features current on new Firebase capabilities."}},{"@type":"Question","name":"How does the tolerance slider work in Firebase Predictions?","acceptedAnswer":{"@type":"Answer","text":"The tolerance slider lets developers choose low, medium, or high risk of false positives when defining a predicted user group. A low tolerance yields a smaller population with fewer false positives, while a high tolerance yields a larger population but more users incorrectly included, such as a 'churn' prediction targeting someone who actually keeps using the app. Developers tuning behavioral targeting trade-offs can track product updates like this via daily.dev."}},{"@type":"Question","name":"Can I create custom predictions in Firebase beyond the built-in churn and spend groups?","acceptedAnswer":{"@type":"Answer","text":"Yes, custom predictions can be created based on custom events set up in an app, such as a level_up event in a game. Once saved, a prediction card populates over time in the Firebase Console just like the built-in Churn, Spend, and Not_Spend groups, and it can be used the same way to target notifications or Remote Config values. Teams building custom engagement logic can follow Firebase feature updates on daily.dev."}}]} ```