Multi-type Feature Mining and Fusion Model for Temporal Prediction

Mining user behavior features is an essential part of recommender systems. As user preferences change dynamically, long-term interest features are very useful for predicting users' future behavior. Hence, the accuracy of temporal prediction will be greatly improved, if we can combine user behavior regularities with the item features. In this paper, we propose a long short-term memory (LSTM) variant, named Multi-type Feature Mining and Fusion (MFMF) model, to mine the long-term dynamic user behavior pattern and the potential relationships between items. We combine these features with user and item attributes to predict which items users will click next. Experiments on two real-world datasets, LastFM dataset and movie dataset, demonstrate the effectiveness of the proposed approach comparing to both traditional and state-of-the- art methods.