Christine Bauer

Date: 16:00 – 16:30, Thursday, 26.11.2020
Location: Teams ICS Colloquium

Title: Compared to what? Music recommendation considering a user’s preferences in relation to the global and country-specific mainstream
Abstract: Algorithmic curation of content is behind a vast majority of online platforms. A frequently addressed problem is to accurately predict the relevance of individual items to users, with the goal of presenting the assumedly most relevant ones as recommendations. This is a complex task because a multitude of factors influence a user’s preferences.
On online music platforms, a recommender system is supposed to assist listeners in navigating the huge catalogs of tens of millions of music recordings. Country-specific variations in music taste are rarely considered; the challenge is that variations seem to be hidden in the “long tail” of the popularity distribution. Besides showcasing some of the country-specific differences in online music consumption behavior, I will demonstrate the performance increase of recommender approaches considering this context compared to taking a globally uniform approach.