Fairness in algorithmic decision-making: The effects of bias mitigation strategies in music recommender systems

Activity: Talk or presentation › Guest lecture › science to science / art to art

Description

Fairness in algorithmic decision-making is a critical concern across various domains. In this talk, I focus on the music domain, where recommender systems have become indispensable, helping users navigate vast catalogs by suggesting similar artists or the next track to play. While these systems’ goal is to recommend the ‘right music to the right person at the right moment’, they often fall short of this ideal, raising questions about fairness and bias. In this talk, I focus on fairness from the perspective of artists, addressing how biases—such as gender bias—manifest in music recommendations and affect artist exposure. I will present research findings on gender bias and explore strategies for their mitigation.
Period20 Nov 2024
Held atBusiness
Degree of RecognitionLocal

Keywords

  • recommender systems
  • fairness
  • algorithmic decision making
  • gender imbalance
  • bias mitigation
  • music
  • artists

Fields of Science and Technology Classification 2012

  • 102 Computer Sciences
  • 509 Other Social Sciences

UN SDGs

This activity contributes to the following UN Sustainable Development Goals (SDGs)

  • SDG 5 - Gender Equality
  • SDG 10 - Reduced Inequalities

Documents & Links

Related content