Recommender Systems: A Multi-Disciplinary Approach
presents a multi-disciplinary approach for the development of recommender systems. It explains different types of pertinent algorithms with their comparative analysis and their role for different applications. This book explains the big data behind recommender systems, the marketing benefits, how to make good decision support systems, the role of machine learning and artificial networks, and the statistical models with two case studies. It shows how to design attack resistant and trust-centric recommender systems for applications dealing with sensitive data.
Features of this book:
Identifies and describes recommender systems for practical uses
Describes how to design, train, and evaluate a recommendation algorithm
Explains migration from a recommendation model to a live system with users
Describes utilization of the data collected from a recommender system to understand the user preferences
Addresses the security aspects and ways to deal with possible attacks to build a robust system
This book is aimed at researchers and graduate students in computer science, electronics and communication engineering, mathematical science, and data science.