On the Influence of User Characteristics on Music Recommendation Algorithms

  • Markus Schedl
  • David Hauger
  • Katayoun Farrahi
  • Marko Tkalčič
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9022)


We investigate a range of music recommendation algorithm combinations, score aggregation functions, normalization techniques, and late fusion techniques on approximately 200 million listening events collected through The overall goal is to identify superior combinations for the task of artist recommendation. Hypothesizing that user characteristics influence performance on these algorithmic combinations, we consider specific user groups determined by age, gender, country, and preferred genre. Overall, we find that the performance of music recommendation algorithms highly depends on user characteristics.


Recommender System Aggregation Function User Characteristic Listening Event Music Recommendation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Baltrunas, L., Kaminskas, M., Ludwig, B., Moling, O., Ricci, F., Lüke, K.-H., Schwaiger, R.: InCarMusic: Context-Aware Music Recommendations in a Car. In: Proc. EC-Web, Toulouse, France (August–September 2011)Google Scholar
  2. 2.
    Cheng, Z., Shen, J.: Just-for-Me: An Adaptive Personalization System for Location-Aware Social Music Recommendation. In: Proc. ICMR, Glasgow, UK (April 2014)Google Scholar
  3. 3.
    de Borda, J.-C.: Mémoire sur les élections au scrutin. Histoire de l’Académie Royale des Sciences (1781)Google Scholar
  4. 4.
    Dror, G., Koenigstein, N., Koren, Y., Weimer, M.: The Yahoo! Music Dataset and KDD-Cup 2011. In: JMLR: Proceedings of KDD-Cup 2011 Competition, pp. 18:3–18 (October 2012)Google Scholar
  5. 5.
    Farrahi, K., Schedl, M., Vall, A., Hauger, D., Tkalčič, M.: Impact of Listening Behavior on Music Recommendation. In: Proc. ISMIR, Taipei, Taiwan (October 2014)Google Scholar
  6. 6.
    Hauger, D., Schedl, M., Košir, A., Tkalčič, M.: The Million Musical Tweets Dataset: What Can We Learn From Microblogs. In: Proc. ISMIR, Curitiba, Brazil (November 2013)Google Scholar
  7. 7.
    Kaminskas, M., Ricci, F., Schedl, M.: Location-aware Music Recommendation Using Auto-Tagging and Hybrid Matching. In: Proc. RecSys 2013, Hong Kong, China (October 2013)Google Scholar
  8. 8.
    Prajapati, B., Dunne, M., Armstrong, R.: Sample Size Estimation and Statistical Power Analyses. Optometry Today 16(7) (2010)Google Scholar
  9. 9.
    Schedl, M., Tkalčič, M.: Genre-based Analysis of Social Media Data on Music Listening Behavior. In: Proc. ACM Multimedia Workshop: ISMM, Orlando, FL, USA (November 2014)Google Scholar
  10. 10.
    Zangerle, E., Gassler, W., Specht, G.: Exploiting Twitter’s Collective Knowledge for Music Recommendations. In: Proc. WWW Workshop: #MSM (April 2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Markus Schedl
    • 1
  • David Hauger
    • 1
  • Katayoun Farrahi
    • 2
  • Marko Tkalčič
    • 1
  1. 1.Department of Computational PerceptionJohannes Kepler UniversityLinzAustria
  2. 2.Department of ComputingGoldsmith’s University of LondonUK

Personalised recommendations