A Survey on Session-based Recommender Systems

Abstract

Recommender systems (RSs) have been playing an increasingly important role for informed consumption, services, and decision-making in the overloaded information era and digitized economy. In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs. Different from other RSs such as content-based RSs and collaborative filtering-based RSs which usually model long-term yet static user preferences, SBRSs aim to capture short-term but dynamic user preferences to provide more timely and accurate recommendations sensitive to the evolution of their session contexts. Although SBRSs have been intensively studied, neither unified problem statements for SBRSs nor in-depth elaboration of SBRS characteristics and challenges are available. It is also unclear to what extent SBRS challenges have been addressed and what the overall research landscape of SBRSs is. This comprehensive review of SBRSs addresses the above aspects by exploring in depth the SBRS entities (e.g., sessions), behaviours (e.g., users' clicks on items) and their properties (e.g., session length). We propose a general problem statement of SBRSs, summarize the diversified data characteristics and challenges of SBRSs, and define a taxonomy to categorize the representative SBRS research. Finally, we discuss new research opportunities in this exciting and vibrant area.

Accepted by ACM Computing Surveys. 39 pages, 163 references, 11 sections, 4 figures and 11 tables, the latest and most comprehensive survey on session-based recommender systems

References in corpus (12)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Deep Reinforcement Learning for Page-wise Recommendations
• Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors
• Empirical Analysis of Session-Based Recommendation Algorithms
• Coupling Learning of Complex Interactions
• Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation
• Contextual Hybrid Session-based News Recommendation with Recurrent Neural Networks
• GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation
• Session-aware Information Embedding for E-commerce Product Recommendation
• Jointly Modeling Intra- and Inter-transaction Dependencies with Hierarchical Attentive Transaction Embeddings for Next-item Recommendation
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• Double-Wing Mixture of Experts for Streaming Recommendations

Cited by in corpus (22)

• Empirical Analysis of Session-Based Recommendation Algorithms
• Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation
• Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations
• Recommender systems based on graph embedding techniques: A comprehensive review
• Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation
• Jointly Modeling Intra- and Inter-transaction Dependencies with Hierarchical Attentive Transaction Embeddings for Next-item Recommendation
• Graph Learning Approaches to Recommender Systems: A Review
• CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network
• Fast-adapting and Privacy-preserving Federated Recommender System
• Graph Learning based Recommender Systems: A Review
• Self-Supervised Graph Co-Training for Session-based Recommendation
• DGTN: Dual-channel Graph Transition Network for Session-based Recommendation
• Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation
• A Simple Deep Personalized Recommendation System
• Deep Dynamic Neural Network to trade-off between Accuracy and Diversity in a News Recommender System
• Session-Based Recommender Systems for Action Selection in GUI Test Generation
• Accelerated learning from recommender systems using multi-armed bandit
• Data Augmentation Using Many-To-Many RNNs for Session-Aware Recommender Systems
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• Sequential Modelling with Applications to Music Recommendation, Fact-Checking, and Speed Reading
• Deep Personalized Re-targeting
• Dynamic Customer Embeddings for Financial Service Applications