Guest Editors
Prof. Yong Zheng
Email: yzheng66@iit.edu
Affiliation: Department of Information Technology and Management, Illinois Institute of Technology, Chicago, IL, USA, 60616
Homepage:
Research Interests: Recommender Systems, Collaborative Filtering, User Modeling
Summary
Recommender systems (RSs) have become an integral part of modern digital experiences, offering personalized suggestions based on user preferences and behaviors. They play a crucial role in real-world applications such as e-commerce platforms, streaming services, social media, and even online news, helping users navigate vast amounts of content. By providing tailored recommendations, these systems enhance user satisfaction, increase engagement, and drive business outcomes. In industries like retail, entertainment, and online services, RSs have become indispensable tools for both customers and businesses, shaping the way information is discovered and consumed.
Collaborative filtering (CF) has emerged as one of the most popular and widely used techniques in the field of recommender systems, largely due to its simplicity and effectiveness in delivering high-quality recommendations. The method leverages user-item interaction data to predict the preferences of users based on the preferences of similar users. The outstanding performance of collaborative filtering algorithms, such as k-Nearest Neighbors, Matrix Factorization, and Deep Learning approaches, has garnered significant attention from the research community. Over the past decade, advancements in these algorithms have significantly improved both the accuracy and relevance of recommendations, making them essential for real-world applications. As a result, collaborative filtering has become a highly active area of research, with ongoing efforts to refine and innovate its methodologies. This Special Issue aims to contribute to this body of knowledge by exploring cutting-edge research and innovative approaches focused on enhancing CF-based Recommender Systems.
Topics of interests include, but are not limited to the following scopes:
· Neighborhood-based CF, such as UserKNN or ItemKNN, etc.
· Latent factor-based CF models, such as matrix or tensor factorization, etc.
· Deep learning-based CF models, such as neural matrix factorization, etc.
· Solutions to address well-known challenges (such as cold-start, sparsity issue, grey-sheep users) in CF
· Ranking methods in CF
· CF optimized by multiple objectives, such as accuracy, novelty, diversity, etc.
· CF models for different types of recommender systems, such as context-aware, cross-domain, multi-criteria, group recommenders, etc.
· Explainability and transparency in CF
Keywords
Recommender system, collaborative filtering, matrix factorization, neighbors, deep learning
Login
Register
Submit a Paper
Propose a Special lssue