In addition, the ratings are also very important to many other information retrieval applications, such as collaborative filtering ratings, definitions, answer questions, multimedia retrieval, text summarization, and online advertising. Utilizing technology in the process of ranking machine learning has led to an innovative model ranking and more effective, and finally to the research area is really new so-called? Learning to rank?. Liu first provide a comprehensive assessment of the various main approaches to learning to rank. These include relational ranking, query-dependent ranking, transfer ratings, and semisupervised ratings. His presentation comes with several examples that apply technology to solve real problems of information retrieval, and with a theoretical discussion of security for the performance ratings. This book is written for researchers and graduate students both in information retrieval and machine learning.