Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation

User modeling is an essential task for online rec- ommender systems. In the past few decades, col- laborative filtering (CF) techniques have been well studied to model users’ long term preferences. Recently, recurrent neural networks (RNN) have shown a great advantage in modeling users’ short term preference. A natural way to improve the rec- ommender is to combine both long-term and short- term modeling. Previous approaches neglect the importance of dynamically integrating these two user modeling paradigms. Moreover, users’ be- haviors are much more complex than sentences in language modeling or images in visual computing, thus the classical structures of RNN such as Long Short-Term Memory (LSTM) need to be upgraded for better user modeling. In this paper, we im- prove the traditional RNN structure by proposing a time-aware controller and a content-aware con- troller, so that contextual information can be well considered to control the state transition. We fur- ther propose an attention-based framework to com- bine users’ long-term and short-term preferences, thus users’ representation can be generated adap- tively according to the specific context. We con- duct extensive experiments on both public and in- dustrial datasets. The results demonstrate that our proposed method outperforms several state-of-art methods consistently.

PDF

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Recommendation Systems Amazon Product Data SLi-Rec AUC 0.8494 # 2
F1 0.7745 # 1

Methods


No methods listed for this paper. Add relevant methods here