With this book, Dongsheng Li et al. offer a comprehensive exploration of recommendation algorithms. They start with traditional recommendation systems, introducing readers to basic principles while critically analyzing their strengths and weaknesses. The transition into deep-learning-based recommender systems marks a major highlight, as the authors delve into how cutting-edge technologies are reshaping the field. This shift from classical methods to modern deep learning techniques makes the book particularly relevant for researchers, data scientists, and artificial intelligent (AI) enthusiasts.

One of the standout features of the book is its practical application. Readers are guided through Microsoft’s open-source project Microsoft Recommenders, which provides hands-on experience with real-world code examples. This practical focus is immensely valuable for professionals looking to build accurate and efficient recommender systems from scratch. The book is suitable for both students and seasoned professionals, offering a deep understanding of both the theoretical and practical aspects of recommendation algorithms.

While the book is rich in technical content, it may be overwhelming for beginners unfamiliar with the core concepts of machine learning and deep learning. A stronger focus on introductory material might help broaden its appeal. However, for readers with a background in these areas, the book is an essential guide to the current state of the art in recommender systems.

Similar works include: Recommender systems handbook [1], a comprehensive resource covering classical and state-of-the-art recommender system techniques; “Deep learning for recommender systems” [2], which focuses on deep learning techniques specifically applied to recommender systems; and Hands-on recommendation systems with Python [3], a practical guide with hands-on examples for building recommender systems using Python.