A Dynamic Recurrent Model for Next Basket Recommendation

By Feng Yu, Qiang Liu, Shu Wu, Liang Wang, Tien-Ping Tan. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2016

514 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/1d87ab4e11143a02afaf28222c4cacb7248a3ad0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Management Science and Operations Research

Citations in the corpus

BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer (2019, background): “, representation of user’s preference which is used to make predictions) with various recurrent architectures and loss functions, including session-based GRU with ranking loss (GRU4Rec) [15], Dynamic REcurrent bAsket Model (DREAM) [59], user-based GRU [7], attention-based GRU (NARM) [28], and improv”
What to Do Next: Modeling User Behaviors by Time-LSTM (2017, methodology): “[Yu et al. , 2016] directly applies RNN to RS, without considering time intervals, while we add time gates to LSTM, which can exploit time intervals to improve the recommendation performance.”
Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation (2019, methodology): “Sequence modeling methods for SR mainly belong to Markov Models [4, 17] and RNNs[8, 9, 15, 27].”
STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation (2018, background): “A constraint is included to avoid coincidental high similarities between rarely visited items as in [4, 20].”
Sequence-Aware Recommender Systems (2018, methodology): “The problem of next-basket recommendation in e-commerce was also the focus of only a few works [72, 94, 110, 116].”
A Survey on Session-based Recommender Systems (2019, methodology): “Basic deep neural networ-ks RNN Long and rigidly ordered sessions Model long-term and high-order sequential dependencies The rigid order assumption is too strong for session data [6],[11],[38], [39],[78],[85], [88],[99],[139]”
Deep Interest Evolution Network for Click-Through Rate Prediction (2018, background): “…system, TDSSM (Song, Elkahky, and He 2016) jointly optimizes long-term and short-term user interests to improve the recommendation quality; DREAM (Yu et al. 2016) uses the structure of recurrent neural network (RNN) to investigate the dynamic representation of each user and the global sequential…”
Controllable Multi-Interest Framework for Recommendation (2020, methodology): “DREAM [57], based on Recurrent Neural Network (RNN), learns a dynamic representation of a user for revealing the user’s dynamic interests.”
Evaluation of session-based recommendation algorithms (2018, methodology): “Generally, it is of course surprising that a recent and popular RNN-based method is not substantially better than longer-existing nearest neighbor approaches.”
STAN: Spatio-Temporal Attention Network for Next Location Recommendation (2021, background): “They have achieved satisfactory performances on variety of tasks, such as session-based recommendation [11, 16], next basket recommendation [37] and next item recommendation [1, 44].”
When Recurrent Neural Networks meet the Neighborhood for Session-Based Recommendation (2017, methodology): “[37] use RNNs for the related task of next basket recommendations, in which, e.”
Sequential Recommendation with User Memory Networks (2018, methodology): “These methods mostly model the local sequential patterns between every two adjacent records [31].”
Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks (2018, methodology): “As one of the most popular neural networks, Recurrent Neural Networks (RNN) together with its variants LSTM and GRU have been widely applied to sequential recommendation, including session-based GRU [15], user-based GRU [5], dynamic recurrent model [36], recurrent recommender network [35], hierarchi”
Dynamic Explainable Recommendation Based on Neural Attentive Models (2019, methodology): “To solve this problem, many models were proposed to capture user multi-step behaviors based on the recurrent neural network (RNN) (Yu et al. 2016; Hidasi et al. 2016; Tan, Xu, and Liu 2016; Donkers, Loepp, and Ziegler 2017; Liu et al. 2016; Song, Elkahky, and He 2016), the convolutional neural netwo”