Users utilize multiple software applications on their devices. Currently, with user permission, each app can utilize user activity data to personalize the user’s experience of using the app. This disclosure describes techniques to securely provide a machine learning model (or other types of predictive model) trained on user activity in a particular app to one or more other apps on the same device. The model can then be used on the same device by the other apps to generate personalized rankings or recommendations for the user, without having access to user activity data. Personalization in this manner can improve the user experience of using apps. The described techniques are implemented with specific user permission and in compliance with applicable regulations.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.