SEM: APP Usage Prediction with Session-Based Embedding

Nowadays smartphone users have installed dozens or even hundreds of APPs on their phones. Predicting APP usage not only helps the mobile phone system to speed up APP launching but also reduces the time for users to search them. In this paper, we focus on a novel session-based APP usage prediction problem that tends to predict a sequence of APPs to be used in a period. We propose a session-based embedding framework called SEM to solve the problem. To deal with the heterogeneity of APP sessions, we present a session embedding algorithm to form uniform feature representation, which alleviates the problem of user sparsity and obtains the vector representation of sessions. Based on session embedding, we train a two-layer GRU-based recursive neural network model for APP usage session prediction. Extensive experiments based on real datasets show that the proposed framework outperforms conventional APP recommendation approaches.