Google Adds Machine Learning Functionality to Firebase Mobile Platform
New machine learning functionality led a host of updates to Google's Firebase mobile development platform.
Firebase is a Mobile-Backend-as-a-Service (MBaaS) offering acquired by Google in 2014, providing mobile and Web app developers with services such as analytics, crash reporting, database and more.
Most of the new Firebase machine learning functionality is provided by ML Kit, a beta offering that simplifies the use of ML for enterprise app developers at all levels.
"If you're new to the space you can use ML Kit's out-of-the-box APIs, like text recognition or face detection, or if you're more experienced you can bring your own custom TensorFlow Lite models and serve them through Firebase," said Francis Ma, head of product, in announcing the beta release of face contours for the face detection API, providing a range of new capabilities.
Google also enhanced Firebase Predictions, which uses ML to help developers predict which users are likely to churn (drop an app), stay engaged with app, spend money or not, and so on.
After introducing Firebase Predictions a year ago as a beta offering, Google at this week's Firebase Summit 2018 in Prague announced it was moving into general availability.
"Wondering what goes go into any given prediction?" said Ma in a blog post. "We added a new details page that shows you what factors the ML model considered (like events, device, user data, etc.) to make that prediction. We also now expose performance metrics for each prediction, letting you see how the prediction has performed historically against actual user behavior, so you can better calibrate your risk tolerance level. And, if you want to do a deeper analysis of prediction data or use it in third party services, you can export your complete prediction dataset to BigQuery."
More details are available on the company's Firebase YouTube channel.
David Ramel is the editor of Visual Studio Magazine.