Music Playlist Recommendation with Long Short-Term Memory

Music playlist recommendation is an important component in modern music streaming services, which is used for improving user experience by regularly pushing personalized music playlists based on users' preferences. In this paper, we propose a novel music playlist recommendation problem, namely Personalized Music Playlist Recommendation (PMPR), which aims to provide a suitable playlist for a user by taking into account her long/short-term preferences and music contextual data. We propose a data-driven framework, which is comprised of two phases: user/music feature extraction and music playlist recommendation. In the first phase, we adopt a matrix factorization technique to obtain long-term features of users and songs, and utilize the Paragraph Vector (PV) approach, an advanced natural language processing technique, to capture music context features, which are the basis of the subsequent music playlist recommendation. In the second phase, we design two Attention-based Long Short-Term Memory (AB-LSTM) models, i.e., typical AB-LSTM model and Improved AB-LSTM (IAB-LSTM) model, to achieve the suitable personalized playlist recommendation. Finally, we conduct extensive experiments using a real-world dataset, verifying the practicability of our proposed methods.