Collaborative Recommendations: algorithms, practical challenges and applications/ Shlomo Berkovsky, Ivan Cantador and Domonkos Tikk

Includes bibliographical references and index

Preface -- Collaborative Filtering: Matrix Completion and Session-Based Recommendation Tasks -- Matrix Factorization for Collaborative Recommendations -- Cutting-Edge Collaborative Recommendation Algorithms: Deep Learning -- Hybrid Collaborative Recommendations: Practical Considerations and Tools to Develop a Recommender -- Context-Aware Recommendations -- Group Recommendations -- User Preference Sources: Explicit vs. Implicit Feedback -- User Preference Elicitation, Rating Sparsity and Cold Start -- Offline and Online Evaluation of Recommendations -- Recommendations Biases and Beyond-Accuracy Objectives in Collaborative Filtering -- Scalability and Distribution of Collaborative Recommenders -- Robustness and Attacks on Recommenders -- Privacy in Collaborative Recommenders -- TV and Movie Recommendations: The Comcast Case -- Music Recommendations -- Contact Recommendations in Social Networks -- Job Recommendations: The XING Case -- Academic Recommendations: The Mendeley Case -- MoocRec.com: Massive Open Online Courses Recommender System -- Food Recommendations -- Clothing Recommendations: The Zalando Case -- Index

Recommender systems are very popular nowadays, as both an academic research field and services provided by numerous companies for e-commerce, multimedia and Web content. Collaborative-based methods have been the focus of recommender systems research for more than two decades.
The unique feature of the compendium is the technical details of collaborative recommenders. The book chapters include algorithm implementations, elaborate on practical issues faced when deploying these algorithms in large-scale systems, describe various optimizations and decisions made, and list parameters of the algorithms.