Change search
ReferencesLink to record
Permanent link

Direct link
Learning Playlist Representations for Automatic Playlist Generation
KTH, School of Computer Science and Communication (CSC).
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Lärande av spellisterepresentationer för automatisk spellistegenerering (Swedish)
Abstract [en]

Spotify is currently the worlds leading music streaming ser-vice. As the leader in music streaming the task of providing listeners with music recommendations is vital for Spotify. Listening to playlists is a popular way of consuming music, but traditional recommender systems tend to fo-cus on suggesting songs, albums or artists rather than pro-viding consumers with playlists generated for their needs.

This thesis presents a scalable and generalizeable approach to music recommendation that performs song selection for the problem of playlist generation. The approach selects tracks related to a playlist theme by finding the charac-terizing variance for a seed playlist and projects candidate songs into the corresponding subspace. Quantitative re-sults shows that the model outperforms a baseline which is taking the full variance into account. By qualitative results the model is also shown to outperform professionally curated playlists in some cases.

Place, publisher, year, edition, pages
Keyword [en]
Playlist generation, machine learning, music recommendation
National Category
Computer Science
URN: urn:nbn:se:kth:diva-172845OAI: diva2:850112
Educational program
Master of Science - Computer Science
Available from: 2015-09-10 Created: 2015-08-31 Last updated: 2015-09-10Bibliographically approved

Open Access in DiVA

fulltext(4358 kB)520 downloads
File information
File name FULLTEXT01.pdfFile size 4358 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 520 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 2189 hits
ReferencesLink to record
Permanent link

Direct link