Название: Recommender Systems: Algorithms and their Applications
Автор: Pushpendu Kar, Monideepa Roy, Sujoy Datta
Издательство: Springer
Год: 2024
Страниц: 174
Язык: английский
Формат: pdf (true), epub
Размер: 19.9 MB

The book includes a thorough examination of the many types of algorithms for recommender systems, as well as a comparative analysis of them. It addresses the problem of dealing with the large amounts of data generated by the recommender system. The book also includes two case studies on recommender system applications in healthcare monitoring and military surveillance. It demonstrates how to create attack-resistant and trust-centric recommender systems for sensitive data applications. This book provides a solid foundation for designing recommender systems for use in healthcare and defense.

Recommendation systems gather information about the likes and dislikes of a user and use various types of complex algorithms to predict what a user may be interested in and send personalized recommendations to users. Brands like Netflix, Amazon, Facebook, Spotify, and YouTube collect information about users and try to predict user preferences. If a person buys a certain product, then suggestions for similar products are sent to the user. If a user likes a particular type of music or movie, then it will try to predict and recommend similar types of music or movies to the user. It is a very vast and interesting area of research but at present, in this book, we have taken some of the most important topics which form the basis of recommender systems, along with some case studies and applications and suggestions for future research directions.

This book will be useful to users who are new to the topic and wish to learn it. It will also be useful to advanced users who know the theory but want to implement or design a system from scratch and can learn from the different types of algorithms.

This book consists of 12 chapters.
Chapter 1 is a general introduction of what is the importance of recommender systems and an overview of the scope of the book and its audience and the motivation behind writing this book.
Chapter 2 is a general overview of all possible types of algorithms for recommendation systems.
Chapter 3 discusses two of the most widely used types of recommender algorithms, content-based systems and collaborative filtering methods, and their features and suitability for implementation.
Chapter 4 discusses the decomposition of the matrix in clustering.
Chapter 5 discusses how to learn to rank users based on various factors and how to detect profiles of false users, along with the Shilling attack example.
Chapter 6 deals with knowledge-based, ensemble-based, and hybrid recommender systems.
Chapter 7 discusses how to deal with the big data associated with recommender systems.
Chapter 8 discusses the existing trust-centric and attack-resistance techniques for recommender systems and proposes different ways to improve the performance of recommendation systems based on both attack and trust.
Chapter 9 shows the steps in building a recommendation engine.
Chapter 10 discusses different types of healthcare recommendation systems, challenges, and the scope of improvements.
Chapter 11 discusses the application of recommender systems to military surveillance.
Chapter 12 discusses the use of recommender systems in different real application domains, existing challenges as well as the scopes and ideas of their improvements.

Contents: