TPGN: A Time-Preference Gate Network for e-commerce purchase intention recognition

Abstract The studies on users’ purchase intentions based on e-commerce data are of great significance to marketers, buyers, and society. Current studies on users’ intentions with traditional machine learning methods usually focus on unique features and are time-consuming. Due to the characteristics of user behaviors and the importance of time sequence, deep learning methods are increasingly applied in relevant studies. In the study, in order to predict online user’s purchase intentions, based on Long-Short Term Memory (LSTM) model, we proposed Time-Preference Gate Network (TPGN). A pair of preference gates and a pair of time interval gates are added to the model. The preference gates are used to capture the users’ category preferences at different time and the time interval gates are used to capture the users’ long-term interest. In our model, through coupling the input gate with the forget gate, the parameters of the model are reduced and the performance is improved. In addition, the difference in user gender leads to the difference in the performance. Extended experiments with two real data sets confirmed that our model performed better than other baseline models.

[1]  Hwanjo Yu,et al.  An encoder-decoder switch network for purchase prediction , 2019, Knowl. Based Syst..

[2]  Jie Tang,et al.  Predicting individual retweet behavior by user similarity: A multi-task learning approach , 2015, Knowl. Based Syst..

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

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

[5]  Yang Yang,et al.  Sequential Modeling of Hierarchical User Intention and Preference for Next-item Recommendation , 2020, WSDM.

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

[7]  Mohamed Morchid,et al.  Parallel Long Short-Term Memory for multi-stream classification , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[8]  Ji-Rong Wen,et al.  CTRec: A Long-Short Demands Evolution Model for Continuous-Time Recommendation , 2019, SIGIR.

[9]  Lei Shi,et al.  Large Scale Purchase Prediction with Historical User Actions on B2C Online Retail Platform , 2014, ArXiv.

[10]  Alex Graves,et al.  Long Short-Term Memory , 2020, Computer Vision.

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

[12]  Qiang Liu,et al.  MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation , 2016, IEEE Transactions on Knowledge and Data Engineering.

[13]  Sule Gündüz Ögüdücü,et al.  Identifying topical influencers on twitter based on user behavior and network topology , 2018, Knowl. Based Syst..

[14]  Paul Covington,et al.  Deep Neural Networks for YouTube Recommendations , 2016, RecSys.

[15]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[16]  Huailin Dong,et al.  Research on statistics-based model for E-commerce user purchase prediction , 2015, 2015 10th International Conference on Computer Science & Education (ICCSE).

[17]  Joemon M. Jose,et al.  A Simple Convolutional Generative Network for Next Item Recommendation , 2018, WSDM.

[18]  Min Chen,et al.  User behaviour modeling, recommendations, and purchase prediction during shopping festivals , 2018, Electron. Mark..

[19]  Longbing Cao,et al.  Attention-Based Transactional Context Embedding for Next-Item Recommendation , 2018, AAAI.

[20]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Liang Wang,et al.  A Hierarchical Contextual Attention-based GRU Network for Sequential Recommendation , 2017, ArXiv.

[22]  Robert Davis,et al.  How gender affects the relationship between hedonic shopping motivation and purchase intentions , 2014 .

[23]  Hamido Fujita,et al.  Extracting Non-redundant Correlated Purchase Behaviors by Utility Measure , 2017, DaWaK.

[24]  Chang Zhou,et al.  Deep Interest Evolution Network for Click-Through Rate Prediction , 2018, AAAI.

[25]  Kai Hu,et al.  Purchase Behavior Prediction in M-Commerce with an Optimized Sampling Methods , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[26]  Fuzhen Zhuang,et al.  Where to Go Next: A Spatio-Temporal Gated Network for Next POI Recommendation , 2019, AAAI.

[27]  Min Wu,et al.  Repeat Buyer Prediction for E-Commerce , 2016, KDD.

[28]  Wei Li,et al.  Multi-Interest Network with Dynamic Routing for Recommendation at Tmall , 2019, CIKM.

[29]  Lina Yao,et al.  Next Item Recommendation with Self-Attention , 2018, ArXiv.

[30]  Chen Zhao,et al.  What to play next? A RNN-based music recommendation system , 2017, 2017 51st Asilomar Conference on Signals, Systems, and Computers.