Deep Learning Recommender Systems

Discover cutting-edge applications of deep learning in recommender systems, one of the main monetization methods of the Internet.

Zhe Wang (Author), Chao Pu (Author), Felice Wang (Author)

9781009447508, Cambridge University Press

Paperback / softback, published 22 May 2025

313 pages
24.3 x 16.8 x 1.7 cm, 0.56 kg

'Reading this book allows you to witness the wealth of resources and engineering practices driving recommendation system development. The authors share unique insights into bridging academic research and industry applications, providing valuable technical perspectives for practitioners and students. The book emphasizes innovative thinking and inspires readers to develop new solutions in recommendation system technologies.' Zi Yang, Google DeepMind

Recommender systems are ubiquitous in modern life and are one of the main monetization channels for Internet technology giants. This book helps graduate students, researchers and practitioners to get to grips with this cutting-edge field and build the thorough understanding and practical skills needed to progress in the area. It not only introduces the applications of deep learning and generative AI for recommendation models, but also focuses on the industry architecture of the recommender systems. The authors include a detailed discussion of the implementation solutions used by companies such as YouTube, Alibaba, Airbnb and Netflix, as well as the related machine learning framework including model serving, model training, feature storage and data stream processing.

1. Growth engine of the internet – recommender system
2. Pre-deep learning era–the evolution of recommender systems
3. Top of the tide – application of deep learning in recommendation system
4. Application of embedding technology in recommender systems
5. Recommender systems from multiple perspectives
6. Engineering implementations in deep learning recommender systems
7. Evaluation in recommender systems
8. Frontier practice of deep learning recommender system
9. Build your own recommender system knowledge framework
Afterword.

Subject Areas: Databases [UN]