CTRec: A Long-Short Demands Evolution Model for Continuous-Time Recommendation

In e-commerce, users' demands are not only conditioned by their profile and preferences, but also by their recent purchases that may generate new demands, as well as periodical demands that depend on purchases made some time ago. We call them respectively short-term demands and long-term demands. In this paper, we propose a novel self-attentive Continuous-Time Recommendation model (CTRec) for capturing the evolving demands of users over time. For modeling such time-sensitive demands, a Demand-aware Hawkes Process (DHP) framework is designed in CTRec to learn from the discrete purchase records of users. More specifically, a convolutional neural network is utilized to capture the short-term demands; and a self-attention mechanism is employed to capture the periodical purchase cycles of long-term demands. All types of demands are fused in DHP to make final continuous-time recommendations. We conduct extensive experiments on four real-world commercial datasets to demonstrate that CTRec is effective for general sequential recommendation problems, including next-item and next-session/basket recommendations. We observe in particular that CTRec is capable of learning the purchase cycles of products and estimating the purchase time of a product given a user.

[1]  Ji-Rong Wen,et al.  A Long-Short Demands-Aware Model for Next-Item Recommendation , 2019, ArXiv.

[2]  Le Song,et al.  Deep Coevolutionary Network: Embedding User and Item Features for Recommendation , 2016, 1609.03675.

[3]  Sang Chan Park,et al.  Customer's time-variant purchase behavior and corresponding marketing strategies: an online retailer's case , 2002 .

[4]  Zhaochun Ren,et al.  Neural Attentive Session-based Recommendation , 2017, CIKM.

[5]  Qiao Liu,et al.  STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation , 2018, KDD.

[6]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[7]  Guokun Lai,et al.  Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks , 2017, SIGIR.

[8]  Hongyuan Zha,et al.  Recurrent Poisson Factorization for Temporal Recommendation , 2020, IEEE Transactions on Knowledge and Data Engineering.

[9]  Yanchi Liu,et al.  Where to Go Next: A Spatio-temporal LSTM model for Next POI Recommendation , 2018, ArXiv.

[10]  Feng Yu,et al.  A Dynamic Recurrent Model for Next Basket Recommendation , 2016, SIGIR.

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

[12]  Nested LSTM : Modeling Taxonomy and Temporal Dynamics in Location-Based Social Network , 2018 .

[13]  Erlend Aune,et al.  Time is of the Essence: A Joint Hierarchical RNN and Point Process Model for Time and Item Predictions , 2018, WSDM.

[14]  Julian J. McAuley,et al.  Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering , 2016, WWW.

[15]  Alex Lobzhanidze,et al.  Buy It Again: Modeling Repeat Purchase Recommendations , 2018, KDD.

[16]  Yang Song,et al.  Multi-Rate Deep Learning for Temporal Recommendation , 2016, SIGIR.

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

[18]  Jinfeng Yi,et al.  Scalable Demand-Aware Recommendation , 2017, NIPS.

[19]  Mejari Kumar,et al.  Connecting Social Media to E-Commerce: Cold-Start Product Recommendation using Microblogging Information , 2018 .

[20]  Ji-Rong Wen,et al.  An Attribute-aware Neural Attentive Model for Next Basket Recommendation , 2018, SIGIR.

[21]  Tat-Seng Chua,et al.  Fast Matrix Factorization for Online Recommendation with Implicit Feedback , 2016, SIGIR.

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

[23]  Robin R. Vallacher,et al.  Dynamical Social Psychology , 1998 .

[24]  C.-Y. Tsai,et al.  A purchase-based market segmentation methodology , 2004, Expert Syst. Appl..

[25]  Wei Wei,et al.  Hierarchical LSTM: Modeling Temporal Dynamics and Taxonomy in Location-Based Mobile Check-Ins , 2019, PAKDD.

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

[27]  Deng Cai,et al.  What to Do Next: Modeling User Behaviors by Time-LSTM , 2017, IJCAI.

[28]  Xin Wang,et al.  Location Recommendation Based on Periodicity of Human Activities and Location Categories , 2013, PAKDD.

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

[30]  David A. McAllester,et al.  Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence , 2009, UAI 2009.

[31]  Dietmar Jannach,et al.  When Recurrent Neural Networks meet the Neighborhood for Session-Based Recommendation , 2017, RecSys.

[32]  Jiawei Han,et al.  TSP: mining top-K closed sequential patterns , 2003, Third IEEE International Conference on Data Mining.

[33]  Jürgen Ziegler,et al.  Sequential User-based Recurrent Neural Network Recommendations , 2017, RecSys.

[34]  Hui Xiong,et al.  Unified Point-of-Interest Recommendation with Temporal Interval Assessment , 2016, KDD.

[35]  Ke Wang,et al.  Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding , 2018, WSDM.

[36]  Julian J. McAuley,et al.  Translation-based Recommendation , 2017, RecSys.

[37]  Alexandros Karatzoglou,et al.  Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks , 2017, RecSys.

[38]  Yuexin Wu,et al.  We know what you want to buy: a demographic-based system for product recommendation on microblogs , 2014, KDD.

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

[40]  Srijan Kumar,et al.  Learning Dynamic Embeddings from Temporal Interaction Networks , 2018 .

[41]  Tao Luo,et al.  Using sequential and non-sequential patterns in predictive Web usage mining tasks , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[42]  Jun Zhang,et al.  A Neural Collaborative Filtering Model with Interaction-based Neighborhood , 2017, CIKM.

[43]  Utkarsh Upadhyay,et al.  Recurrent Marked Temporal Point Processes: Embedding Event History to Vector , 2016, KDD.

[44]  Jason Eisner,et al.  The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process , 2016, NIPS.