Prophet

Abstract

A variety of applications (app) installed on smart phones do greatly enrich our lives, but make it more difficult to organize our screens and folders. Predicting apps that will be in use next can benefit users a lot. In this poster, we propose some light-weighted Bayesian methods to predict the next app based on the app usage history. The evaluation on Mobile Data Challenge (MDC) dataset gives very encouraging results. In addition, we suggest a natural way to integrate the app prediction features to the user interface. Users would find it convenient to access the predicted apps with simple touches.