AppRush: Using Dynamic Shortcuts to Facilitate Application Launching on Mobile Devices

Abstract

When there are many applications (apps) installed on a mobile device, the simple task of launching an app could become inconvenient, as the user may need to swipe the screen several times to find the desired app. In this paper, we present AppRush, an adaptive user interface solution for mobile devices, which uses dynamic shortcuts to facilitate app launching. AppRush predicts the apps most likely to be launched at a certain time based on the user's app usage history. The prediction model utilizes multiple features including recency, frequency, duration, time distribution and app launching sequence. AppRush updates the app shortcuts dynamically on the home screen according to the prediction result. With the correct prediction, the user is able to launch an app from the home screen via one-tap. The evaluation performed on real-world user data demonstrates the effectiveness of the proposed prediction algorithm. In addition, AppRush maintains a low system overhead, which makes it applicable for running on battery-driven mobile devices.