Abstract
When a large number of applications are installed on a user device, a user may forget to use an app they have not engaged with or that they use infrequently. While reminders can improve app engagement, reminders delivered at inopportune times may not improve user engagement and may be perceived negatively. This disclosure describes techniques to personalize the timings of reminders to users to open installed apps. With user permission, machine learning (ML) is used to predict a suitable time to notify the user to open an app. A trained ML model analyzes permitted user and app data to personalize the timing of post-installation reminders, dynamically scheduling notifications for times when the user is most likely to open the app. Advantages of the described techniques include boosting post-install engagement, improving the quality and usefulness of notifications, proactively displaying applications that a user is likely to use, enabling developers to achieve higher install-to-open conversions, improving long-term usage of apps, etc.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Ji, Haifeng; Ma, Xiaoxue; Le, Giang Huong; Wei, Hua; Chen, Haoyu; and Kokare, Kiran, "Optimizing the Timing of Reminders for Unopened Apps", Technical Disclosure Commons, (July 07, 2026)
https://www.tdcommons.org/dpubs_series/10831