The new gatekeepers: searching for bias in Spotify's curated playlists

On streaming platforms, playlists have become the backbone of listening. A high ranking in a top playlist is often the difference between success and failure for a new song. McKenzie et al. (2021) find that songs that feature other artists perform better than songs that don’t feature other artists. At the same time Waldfogel et al. (2021) provide evidence Spotify’s playlist curators bias certain songs in their ranking decisions. In light of these two distinct findings, we ask if it’s possible that the ‘feature’ effect observed by Mckenzie et al. is driven by a bias in playlist rankings? We ask a similar question of the success of major label and local songs. To answer our research questions we focus on the popular New Music Friday playlists, which rank new music the day of release. We first conduct an ‘outcomes-based’ test to identify bias, finding that feature and major label songs receive lower ex-ante playlist ranks than their ultimate streaming outcome warrants across the US, Canadian, UK and Australian playlists. We also find curators of the non-US playlists rank local songs more than their streaming outcome warrants. Second, we build a weekly streaming model of top 200 chart songs for the same countries. Using artist-fixed effects, we provide evidence that the feature artist effect observed by McKenzie et al. exists beyond the US, and that its strong enough to offset the unfavourable playlist rankings. Our results show Spotify’s curators do not always rank songs strictly in terms of appeal, and speculate that they may be motivated to ‘level the playing field’ between certain groups of artist and support local content.