BTC$80,260 -0.38%ETH$2,324 -0.24%USDT$1.00 +0.02%BNB$743 -0.74%SOL$101 -0.18%XRP$1.29 -1.79%ADA$0.20 -0.13%DOGE$0.08 +0.38%
Prices · CoinGecko

How Machine Learning is Useful in Mobile App Development

TechnologyBit News Today1 min read

Machine learning reached everyday phone apps by two routes: services that learn from user behaviour, such as playlists and dating profiles, and developer toolkits that run trained models directly on the handset. The table lists the launches that set this pattern between 2015 and 2020, together with the figures each company reported.

DateApp or toolkitMachine learning featureReported result or scale
Jul 2015Spotify Discover WeeklyPersonal weekly playlist driven partly by collaborative filtering of listening patterns40 million users and nearly 5 billion streamed tracks by May 2016
2015-2016Spotify back endWeekly regeneration of every user's playlist100 million playlists rebuilt each Sunday night from about a terabyte of fresh data
15 Sep 2015Snapchat LensesReal-time face tracking taken from Ukrainian startup LookseryPurchase price of $150 million later confirmed in Snap's IPO filing
Oct 2016Tinder Smart PhotosRotates profile pictures and reorders them by how other users swipeUp to 12% more matches in Tinder's own tests
Jun 2017Apple Core MLFramework for running trained models on Apple devices, used by Siri, Camera and QuickTypeConverts models from Keras, Caffe, scikit-learn, libsvm and XGBoost
12 Sep 2017Apple A11 BionicDual-core Neural Engine for Face ID and AnimojiApple claimed 600 billion operations per second; closed to third-party apps at launch
8 May 2018Google ML Kit for FirebaseReady-made APIs for Android and iOS: text, faces, barcodes, image labels, landmarksReleased in beta; face and barcode detection on device, landmark recognition in the cloud
Jun 2020Standalone ML KitOn-device APIs split from Firebase into their own SDKApps no longer need a Firebase project to use them

Sources: TechCrunch, Engadget, IEEE Spectrum, MIT Technology Review, Kyiv Post, Android Authority, InfoQ, CNBC, Firebase Blog, VentureBeat, Android Developers Blog.