Music Recommendation and Discovery

As more and more of us use automated music recommendation, this book describes how these systems work, explores some of their limitations, offers techniques for evaluating their effectiveness, and uses real-life examples to show how to build them effectively.

In the last 15 years we have seen a major transformation in the world of music. - sicians use inexpensive personal computers instead of expensive recording studios to record, mix and engineer music. Musicians use the Internet to distribute their - sic for free instead of spending large amounts of money creating CDs, hiring trucks and shipping them to hundreds of record stores. As the cost to create and distribute recorded music has dropped, the amount of available music has grown dramatically. Twenty years ago a typical record store would have music by less than ten thousand artists, while today online music stores have music catalogs by nearly a million artists. While the amount of new music has grown, some of the traditional ways of ?nding music have diminished. Thirty years ago, the local radio DJ was a music tastemaker, ?nding new and interesting music for the local radio audience. Now - dio shows are programmed by large corporations that create playlists drawn from a limited pool of tracks. Similarly, record stores have been replaced by big box reta- ers that have ever-shrinking music departments. In the past, you could always ask the owner of the record store for music recommendations. You would learn what was new, what was good and what was selling. Now, however, you can no longer expect that the teenager behind the cash register will be an expert in new music, or even be someone who listens to music at all.

Starts with a formalization of the general recommendation problem Presents the pros and cons of most-used recommendation approaches, with a focus on the music domain Combines elements from recommender systems, complex network analysis, music information retrieval, and personalization Emphasizes "user's perceived quality" versus "system's predictive accuracy" Includes supplementary material: sn.pub/extras

Klappentext

With so much more music available these days, traditional ways of finding music have diminished. Today radio shows are often programmed by large corporations that create playlists drawn from a limited pool of tracks. Similarly, record stores have been replaced by big-box retailers that have ever-shrinking music departments. Instead of relying on DJs, record-store clerks or their friends for music recommendations, listeners are turning to machines to guide them to new music.

In this book, Òscar Celma guides us through the world of automatic music recommendation. He describes how music recommenders work, explores some of the limitations seen in current recommenders, offers techniques for evaluating the effectiveness of music recommendations and demonstrates how to build effective recommenders by offering two real-world recommender examples. He emphasizes the user's perceived quality, rather than the system's predictive accuracy when providing recommendations, thus allowing users to discover new music by exploiting the long tail of popularity and promoting novel and relevant material ("non-obvious recommendations"). In order to reach out into the long tail, he needs to weave techniques from complex network analysis and music information retrieval.

Aimed at final-year-undergraduate and graduate students working on recommender systems or music information retrieval, this book presents the state of the art of all the different techniques used to recommend items, focusing on the music domain as the underlying application.

Inhalt
The Recommendation Problem.- Music Recommendation.- The Long Tail in Recommender Systems.- Evaluation Metrics.- Network-Centric Evaluation.- User-Centric Evaluation.- Applications.- Conclusions and Further Research.