Название: Recommender Systems: Frontiers and Practices
Автор: Dongsheng Li, Jianxun Lian, Le Zhang, Kan Ren
Издательство: Springer/House of Electronics Industry
Год: 2024
Страниц: 292
Язык: английский
Формат: pdf (true), epub
Размер: 25.0 MB

This book starts from the classic recommendation algorithms, introduces readers to the basic principles and main concepts of the traditional algorithms, and analyzes their advantages and limitations. Then, it addresses the fundamentals of Deep Learning, focusing on the deep-learning-based technology used, and analyzes problems arising in the theory and practice of recommender systems, helping readers gain a deeper understanding of the cutting-edge technology used in these systems. Lastly, it shares practical experience with Microsoft 's open source project Microsoft Recommenders. Readers can learn the design principles of recommendation algorithms using the source code provided in this book, allowing them to quickly build accurate and efficient recommender systems from scratch.

The emergence of Deep Learning has greatly changed the development of recommendation technology, and it is necessary for researchers and technicians in the field of recommender systems to have a deep understanding of deep learning-based recommendation technology. First, the development of technology is usually like a spiral, and recommendation technology is not exceptional. We can often see the shadows of traditional recommendation technologies behind many new methods and technologies, so that it is very important to connect traditional recommendation technologies with recent deep learning-based recommendation technologies. Therefore, this book spends a lot of space introducing classic recommendation technologies. Secondly, recommendation technology is not limited to Internet applications. There are also a large number of recommendation scenarios in our daily lives. Traditional industries can also use recommender systems to reform their business or management. Therefore, this book focuses on introducing the basic technologies that are not application-specific, so that researchers at different stages and technicians in different industries can all benefit from it. Finally, the recommender system is an application-oriented area. In addition to the learning of methods and principles, it is more important to learn how to design and implement industrial-level recommender systems. Therefore, this book presents to readers how to apply the theory into the practice based on the open source project of Microsoft Recommenders.

To allow readers with different backgrounds and from different industries clearly and completely understand the cause and effect of recommendation technology, this book attempts to view recommender systems from a broader perspective. First, this book starts with classic recommendation algorithms, introduces the basic principles and main concepts of the traditional recommendation algorithms, analyzes their advantages and limitations, and lays the foundation for readers to better understand deep learning-based recommendation technology. Then, this book introduces the basic knowledge of Deep Learning, focuses on deep learning-based recommendation technology, and analyzes the key problems of recommender systems from both theoretical and practical perspectives, so that readers can gain a deeper understanding of the cutting-edge technologies of recommender systems. Finally, this book introduces the practical experience of recommender systems based on Microsoft Recommenders, an open source project of Microsoft. Based on the source code provided in this book, readers can learn the design principles and practical methods of recommendation algorithms in depth, and can quickly build an accurate and efficient recommender system from scratch based on this book.