skip to main content
10.1145/3018661.3018718acmconferencesArticle/Chapter ViewAbstractPublication PageswsdmConference Proceedingsconference-collections
research-article

Groove Radio: A Bayesian Hierarchical Model for Personalized Playlist Generation

Published: 02 February 2017 Publication History

Abstract

This paper describes an algorithm designed for Microsoft's Groove music service, which serves millions of users world wide. We consider the problem of automatically generating personalized music playlists based on queries containing a ``seed'' artist and the listener's user ID. Playlist generation may be informed by a number of information sources including: user specific listening patterns, domain knowledge encoded in a taxonomy, acoustic features of audio tracks, and overall popularity of tracks and artists. The importance assigned to each of these information sources may vary depending on the specific combination of user and seed~artist.
The paper presents a method based on a variational Bayes solution for learning the parameters of a model containing a four-level hierarchy of global preferences, genres, sub-genres and artists. The proposed model further incorporates a personalization component for user-specific preferences. Empirical evaluations on both proprietary and public datasets demonstrate the effectiveness of the algorithm and showcase the contribution of each of its components.

References

[1]
O. Barkan and N. Koenigstein. Item2vec: Neural item embedding for collaborative ltering. arXiv preprint arXiv:1603.04259, 2016.
[2]
C. M. Bishop. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag New York, Inc., 2006.
[3]
D. Bogdanov, M. Haro, F. Fuhrmann, A. Xambó, E. GóMez, and P. Herrera. Semantic audio content-based music recommendation and visualization based on user preference examples. Inf. Process. Manage., 2013.
[4]
G. Bonnin and D. Jannach. Automated generation of music playlists: Survey and experiments. ACM Comput. Surv., 2015.
[5]
S. J. Cunningham, D. Bainbridge, and A. Falconer. More of an Art than a Science': Supporting the Creation of Playlists and Mixes. In Proceedings of ISMIR, 2006.
[6]
C. Decoro, Z. Barutcuoglu, and R. Fiebrink. Bayesian aggregation for hierarchical genre classification. In Proceedings of ISMIR, 2007.
[7]
M. Dopler, M. Schedl, T. Pohle, and P. Knees. Accessing music collections via representative cluster prototypes in a hierarchical organization scheme. In Proceedings of ISMIR, 2008.
[8]
G. Dror, N. Koenigstein, and Y. Koren. Yahoo ! music recommendations : Modeling music ratings with temporal dynamics and item taxonomy. In Proceedings of RecSys, 2011.
[9]
T. Fawcett. An introduction to ROC analysis. Pattern Recognition Letters, 27:861{874, 2006.
[10]
B. Ferwerda and M. Schedl. Enhancing music recommender systems with personality information and emotional states: A proposal. In Proceedings of UMAP, 2014.
[11]
M. Gillhofer and M. Schedl. Iron maiden while jogging, debussy for dinner? In X. He, S. Luo, D. Tao, C. Xu, J. Yang, and M. A. Hasan, editors, Proceedings of MMM, 2015.
[12]
S. Gopal, Y. Yang, B. Bai, and A. Niculescu-mizil. Bayesian models for large-scale hierarchical classification. In Proceedings of NIPS, 2012.
[13]
N. Hariri, B. Mobasher, and R. Burke. Context-aware music recommendation based on latent topic sequential patterns. In Proceedings of Recsys, 2012.
[14]
T. S. Jaakkola and M. I. Jordan. A variational approach to bayesian logistic regression models and their extensions. In Workshop on Arti cial Intelligence and Statistics, 1996.
[15]
D. Jannach, L. Lerche, and I. Kamehkhosh. Beyond "Hitting the Hits": Generating coherent music playlist continuations with the right tracks. In Proceedings of NIPS.
[16]
M. I. Jordan, Z. Ghahramani, T. S. Jaakkola, and L. K. Saul. An introduction to variational methods for graphical models. Journal of Machine Learning, 1999.
[17]
P. Knees, T. Pohle, M. Schedl, and G. Widmer. Combining audio-based similarity with web-based data to accelerate automatic music playlist generation. In Proceedings of MIR, 2006.
[18]
Y. Koren, R. M. Bell, and C. Volinsky. Matrix factorization techniques for recommender systems. IEEE Computer, 2009.
[19]
J. Lee. How similar is too similar?: Exploring users' perceptions of similarity in playlist evaluation. In Proceedings of ISMIR, 2011.
[20]
L. V. D. Maaten and G. Hinton. Visualizing data using t-sne. Journal of Machine Learning Research, 2008.
[21]
D. J. MacKay. The evidence framework applied to classification networks. Neural Computation, 1992.
[22]
B. Mcfee, L. Barrington, and G. Lanckriet. Learning similarity from collaborative lters. In Proceedings of ISMIR, 2010.
[23]
B. Mcfee and G. Lanckriet. Heterogeneous embedding for subjective artist similarity. In Proceedings of ISMIR, 2009.
[24]
B. McFee and G. Lanckriet. Learning multi-modal similarity. Journal of Machine Learning, 2011.
[25]
A. Mnih. Taxonomy-informed latent factor models for implicit feedback. In JMLR W&CP, 2012.
[26]
U. Paquet and N. Koenigstein. One-class collaborative filtering with random graphs. In Proceedings of WWW, 2013.
[27]
S. Pauws. Pats: Realization and user evaluation of an automatic playlist generator. In Proceedings of ISMIR, 2002.
[28]
S. Pauws, W. Verhaegh, and M. Vossen. Music playlist generation by adapted simulated annealing. Information Sciences, 2008.
[29]
D. A. Reynolds, T. F. Quatieri, and R. B. Dunn. Speaker veri cation using adapted gaussian mixture models. Digital Signal Processing, 2000.
[30]
M. Schedl and D. Hauger. Tailoring music recommendations to users by considering diversity, mainstreaminess, and novelty. In Proceedings of SIGIR, 2015.
[31]
M. Slaney, K. Weinberger, and W. White. Learning a metric for music similarity. In Proceedings of ISMIR, 2008.
[32]
R. Turrin, M. Quadrana, A. Condorelli, R. Pagano, and P. Cremonesi. 30music listening and playlists dataset. In Proceedings of RecSys, 2015.
[33]
A. van den Oord, S. Dieleman, and B. Schrauwen. Deep content-based music recommendation. Proceedings of NIPS, 2013.

Cited By

View all
  • (2024)Surveying More Than Two Decades of Music Information Retrieval Research on PlaylistsACM Transactions on Intelligent Systems and Technology10.1145/368839815:6(1-68)Online publication date: 12-Aug-2024
  • (2024)Probabilistic Path Integration with Mixture of Baseline DistributionsProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679641(570-580)Online publication date: 21-Oct-2024
  • (2023)The Role of Serendipity in User-Curated Music PlaylistsProceedings of the 12th Knowledge Capture Conference 202310.1145/3587259.3627552(140-147)Online publication date: 5-Dec-2023
  • Show More Cited By

Index Terms

  1. Groove Radio: A Bayesian Hierarchical Model for Personalized Playlist Generation

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    WSDM '17: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining
    February 2017
    868 pages
    ISBN:9781450346757
    DOI:10.1145/3018661
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 02 February 2017

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. personalization
    2. playlist generation
    3. radio
    4. recommendation
    5. variational inference

    Qualifiers

    • Research-article

    Conference

    WSDM 2017

    Acceptance Rates

    WSDM '17 Paper Acceptance Rate 80 of 505 submissions, 16%;
    Overall Acceptance Rate 498 of 2,863 submissions, 17%

    Upcoming Conference

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)7
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 19 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Surveying More Than Two Decades of Music Information Retrieval Research on PlaylistsACM Transactions on Intelligent Systems and Technology10.1145/368839815:6(1-68)Online publication date: 12-Aug-2024
    • (2024)Probabilistic Path Integration with Mixture of Baseline DistributionsProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679641(570-580)Online publication date: 21-Oct-2024
    • (2023)The Role of Serendipity in User-Curated Music PlaylistsProceedings of the 12th Knowledge Capture Conference 202310.1145/3587259.3627552(140-147)Online publication date: 5-Dec-2023
    • (2022)Personalized Music Playlist Generation Method for Placing the Listener in a Positive MoodInternational Journal of Affective Engineering10.5057/ijae.IJAE-D-21-0002121:3(159-168)Online publication date: 2022
    • (2022)Controllable Music Playlist Generation Based on Knowledge Graph and Reinforcement LearningSensors10.3390/s2210372222:10(3722)Online publication date: 13-May-2022
    • (2021)Stay Tuned! An Investigation of Content Substitution, the Listener as Curator and Other Innovations in Broadcast RadioProceedings of the 2021 ACM International Conference on Interactive Media Experiences10.1145/3452918.3458793(120-133)Online publication date: 21-Jun-2021
    • (2020)Inferring the Causal Impact of New Track Releases on Music Recommendation Platforms through Counterfactual PredictionsProceedings of the 14th ACM Conference on Recommender Systems10.1145/3383313.3418491(687-691)Online publication date: 22-Sep-2020
    • (2020)Music Playlist Generation Based on Reinforcement Learning Using Acoustic Feature Map2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)10.1109/GCCE50665.2020.9291748(942-943)Online publication date: 13-Oct-2020
    • (2020)Recommending Music Curators: A Neural Style-Aware ApproachAdvances in Information Retrieval10.1007/978-3-030-45439-5_13(191-204)Online publication date: 8-Apr-2020
    • (2019)Random Playlists Smoothly Commuting Between StylesACM Transactions on Multimedia Computing, Communications, and Applications10.1145/336174215:4(1-20)Online publication date: 16-Dec-2019
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media