Personalized Machine Learning

Description

Every day we interact with machine learning systems offering individualized predictions for our entertainment, social connections, purchases, or health. These involve several modalities of data, from sequences of clicks to text, images, and social interactions. This book introduces common principles and methods that underpin the design of personalized predictive models for a variety of settings and modalities. The book begins by revising 'traditional' machine learning models, focusing on adapting them to settings involving user data, then presents techniques based on advanced principles such as matrix factorization, deep learning, and generative modeling, and concludes with a detailed study of the consequences and risks of deploying personalized predictive systems. A series of case studies in domains ranging from e-commerce to health plus hands-on projects and code examples will give readers understanding and experience with large-scale real-world datasets and the ability to design models and systems for a wide range of applications.

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.

'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 'A comprehensive, authoritative, and systematic introduction to personalized machine learning. Starting with essential concepts on machine learning, the book covers multiple architectures of recommender systems as well as personalized models of text and visual data. A great book for both new learners and advanced researchers!' Jiawei Han, Michael-Aiken Chair Professor, University of Illinois at Urbana-Champaign