Spotify is an online music streaming service with over 140 million active users and over 30 million tracks. One of its popular features is the ability to create playlists, and the service currently hosts over 2 billion playlists.
This year's challenge focuses on music recommendation, specifically the challenge of automatic playlist continuation. By suggesting appropriate songs to add to a playlist, a Recommender System can increase user engagement by making playlist creation easier, as well as extending listening beyond the end of existing playlists.
The RecSys Challenge 2018 is organized by Spotify, The University of Massachusetts, Amherst, and Johannes Kepler University, Linz. For information
about the ACM RecSys Challenge Workshop, the Challenge timeline, and information on paper submission and selection criteria, be sure to visit the
main ACM RecSys Challenge page.
The goal of the challenge is to develop a system for the task of automatic playlist continuation. Given a set of playlist features, participants’ systems shall generate a list of recommended tracks that can be added to that playlist, thereby ‘continuing’ the playlist.
As part of this challenge, Spotify has released the Million Playlist Dataset. It comprises a set of 1,000,000 playlists that have been created by Spotify
users, and includes playlist titles, track listings and other metadata. In order to access the Million Playlist Dataset you will need to
register for the challenge and agree to the
license terms. Once you've registered you can download the data from the the dataset page.
You can only participate in the challenge and download the Million Playlist Dataset if you sign the license agreement.
The complete terms and conditions can be found on the license agreement page.
More information about the challenge details regarding evaluation, metrics, submission format, etc. can be found on
the challenge rules page.
Detailed information about the terms and conditions of the challenge can be found in the Terms and
Conditions. For information on the Million Playlist Dataset visit
the dataset page.
See the official
RecSys Challenge website for information about the challenge timeline, workshop, paper submission and selection.
Details about participation
- To participate, you must register as part of a team. A team can be as large or small as you want. You can only be on one team. Teams must
include at least one academic particpant.
- Academic participants in the challenge must be a current faculty member, research employee, or student from an accredited university.
- Academic participants in the challenge get full access to the Million Playlist dataset. Non-academic particpants get accees to a smaller
subset of the MPD.
- The Million Playlist Dataset released as part of this Challenge can be used only to prepare your submission for this Challenge.
You are not allowed to do anything else with it.
- There are two tracks. Make sure you understand the rules for each track. Detailed rules for each track can be found on the Challenge rules page.
- Your entry in the challenge must include the source code. A third party should be able to use your submitted source to regenerate your results.
- Your source code must be released under an open-source license (Apache 2.0).
- Cedric De Boom
- Jean Garcia-Gathright
- Paul Lamere
- James McInerney
- Vidhya Murali
- Hugh Rawlinson
- Sravana Reddy
- Romain Yon