Julian McAuley has been a Professor at UC San Diego since 2014. Personalized Machine Learning is the main research area of his lab, with applications ranging from personalized recommendation, to dialog, healthcare, and fashion design. He regularly collaborates with industry on these topics, including with Amazon, Facebook, Microsoft, Salesforce, and Etsy. His work has been selected for several awards, including an NSF CAREER award, and faculty awards from Amazon, Salesforce, Facebook, and Qualcomm, among others.

• 1. Introduction; Part I. Machine Learning Primer: 2. Regression and feature engineering; 3. Classification and the learning pipeline; Part II. Fundamentals of Personalized Machine Learning: 4. Introduction to recommender systems; 5. Model-based approaches to recommendation; 6. Content and structure in recommender systems; 7. Temporal and sequential models; Part III. Emerging Directions in Personalized Machine Learning: 8. Personalized models of text; 9. Personalized models of visual data; 10. The consequences of personalized machine learning; References; Index.

'This is an excellent book on personalization and recommendations systems, from a prominent leader in the field. The book successfully serves multiple purposes: It is excellent as a reference, providing a comprehensive picture of the state of the art on recommendation systems, including not only the technical details, but also social-impact issues, like fairness, 'filter bubbles' ('echo chambers'),and the closely related topic of diversity. The second role is as a teaching resource: it has a gentle, intuitive coverage of all the necessary concepts and it provides exercises with solutions, as well as class projects. The third role is as a general, well-motivated introduction to almost all ML topics: supervised methods like regression and classification; unsupervised ones like matrix factorization; time series tools like Markov chains; text analysis; and deep learning. The final role is as a research tool: for practitioners and researchers, the book provides python code as well as a well-organized web site with about 30 datasets that researchers could use to stress-test their new algorithms.' Christos Faloutsos, Carnegie Mellon University