A Genre-Based Analysis of New Music Streaming at Scale


The rise of on-demand music streaming platforms and novel recommendation algorithms have brought a transformative shift in music listening, where users have an effectively endless supply of new music to discover. This study aims to understand novel music streaming patterns, operationalizing novel music as new music releases that are new to everyone, from the perspective of genres. Leveraging tracks, users, and streaming data from Spotify, we empirically analyze streaming patterns of 282K new music releases. We find that new releases in genres that often serve functional purposes, such as classical music for relaxation, are consumed less. Surprisingly, new releases in Pop generally do not exhibit high consumption rates despite being characterized as popular music. From examining 1 million users’ historical genre preferences, we observe that users’ new release preferences are distinct from their overall music preferences, although past genre affinities and proclivity for newer content can predict new music consumption. Our findings present important implications for new music recommendation strategies on music streaming platforms and broader contributions to understanding the dynamics of music discovery.


May 2024 | Yijun Tian, Maryam Aziz, Alice Wang, Enrico Palumbo and Hugues Bouchard

Structural Podcast Content Modeling with Generalizability

Yijun Tian, Maryam Aziz, Alice Wang, Enrico Palumbo and Hugues Bouchard

May 2024 | The Web Conference

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks

Marco De Nadai, Francesco Fabbri, Paul Gigioli, Alice Wang, Ang Li, Fabrizio Silvestri, Laura Kim, Shawn Lin, Vladan Radosavljevic, Sandeep Ghael, David Nyhan, Hugues Bouchard, Mounia Lalmas-Roelleke, Andreas Damianou

May 2024 | The Web Conference (GFM workshop)

Towards Graph Foundation Models for Personalization

Andreas Damianou, Francesco Fabbri, Paul Gigioli, Marco De Nadai, Alice Wang, Enrico Palumbo, Mounia Lalmas