Sequential Modeling of Hierarchical User Intention and Preference for Next-item Recommendation

The next-item recommendation has attracted great research interests with both static and dynamic users' preferences considered. Existing approaches typically utilize user-item binary relations, and assume a flat preference distribution over items for each user. However, this assumption neglects the hierarchical discrimination between user intentions and user preferences, causing the methods have limited capacity to depict intention-specific preference. In fact, a consumer's purchasing behavior involves a natural sequential process, i.e., he/she first has an intention to buy one type of items, followed by choosing a specific item according to his/her preference under this intention. To this end, we propose a novel key-array memory network (KA-MemNN), which takes both user intentions and preferences into account for next-item recommendation. Specifically, the user behavioral intention tendency is determined through key addressing. Further, each array outputs an intention-specific preference representation of a user. Then, the degree of user's behavioral intention tendency and intention-specific preference representation are combined to form a hierarchical representation of a user. This representation is further utilized to replace the static profile of users in traditional matrix factorization for the purposes of reasoning. The experimental results on real-world data demonstrate the advantages of our approach over state-of-the-art methods.

[1]  Pengfei Wang,et al.  Learning Hierarchical Representation Model for NextBasket Recommendation , 2015, SIGIR.

[2]  Julian J. McAuley,et al.  Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[3]  Longbing Cao,et al.  Interpretable Recommendation via Attraction Modeling: Learning Multilevel Attractiveness over Multimodal Movie Contents , 2018, IJCAI.

[4]  Yunming Ye,et al.  DeepFM: An End-to-End Wide & Deep Learning Framework for CTR Prediction , 2018, ArXiv.

[5]  Yuanzhi Li,et al.  Convergence Analysis of Two-layer Neural Networks with ReLU Activation , 2017, NIPS.

[6]  Fei Wu,et al.  HST-LSTM: A Hierarchical Spatial-Temporal Long-Short Term Memory Network for Location Prediction , 2018, IJCAI.

[7]  Junping Du,et al.  A Sequential Approach to Market State Modeling and Analysis in Online P2P Lending , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[8]  Alexandros Karatzoglou,et al.  Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations , 2016, RecSys.

[9]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Ji-Rong Wen,et al.  Taxonomy-Aware Multi-Hop Reasoning Networks for Sequential Recommendation , 2019, WSDM.

[11]  Hui Xiong,et al.  Sequential Recommender System based on Hierarchical Attention Networks , 2018, IJCAI.

[12]  Enhong Chen,et al.  Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors , 2018, KDD.

[13]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[14]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[15]  Hui Xiong,et al.  Time-aware metric embedding with asymmetric projection for successive POI recommendation , 2018, World Wide Web.

[16]  Philip S. Yu,et al.  Effective Next-Items Recommendation via Personalized Sequential Pattern Mining , 2012, DASFAA.

[17]  Samuel Kaski,et al.  Interactive intent modeling , 2014, Commun. ACM.

[18]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[19]  Bin Shen,et al.  Collaborative Memory Network for Recommendation Systems , 2018, SIGIR.

[20]  Tat-Seng Chua,et al.  Neural Factorization Machines for Sparse Predictive Analytics , 2017, SIGIR.

[21]  Geoffrey E. Hinton,et al.  Restricted Boltzmann machines for collaborative filtering , 2007, ICML '07.

[22]  Yongfeng Zhang,et al.  Sequential Recommendation with User Memory Networks , 2018, WSDM.

[23]  Hui Xiong,et al.  Recurrent Convolutional Neural Network for Sequential Recommendation , 2019, WWW.

[24]  Panos Kalnis,et al.  Personalized trajectory matching in spatial networks , 2014, The VLDB Journal.

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  Guandong Xu,et al.  Diversifying Personalized Recommendation with User-session Context , 2017, IJCAI.

[27]  Lars Schmidt-Thieme,et al.  Factorizing personalized Markov chains for next-basket recommendation , 2010, WWW '10.

[28]  Alex Beutel,et al.  Recurrent Recommender Networks , 2017, WSDM.

[29]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[30]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[31]  Wei Zhang,et al.  Improving Entity Recommendation with Search Log and Multi-Task Learning , 2018, IJCAI.

[32]  George Karypis,et al.  FISM: factored item similarity models for top-N recommender systems , 2013, KDD.

[33]  Jure Leskovec,et al.  Friendship and mobility: user movement in location-based social networks , 2011, KDD.

[34]  Tat-Seng Chua,et al.  Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks , 2017, IJCAI.

[35]  Lina Yao,et al.  Next Item Recommendation with Self-Attentive Metric Learning , 2018 .