It's Not You, It's Me: The Impact of Choice Models and Ranking Strategies on Gender Imbalance in Music Recommendation

TL;DR

This paper investigates how ranking strategies and user choice models influence gender fairness in music recommender systems, highlighting the significant impact of re-ranking strategies on reducing gender bias over time.

Contribution

It provides a simulation-based analysis of the relative effects of algorithmic ranking strategies versus user behavior on gender fairness in music recommendations.

Findings

Re-ranking strategies significantly improve gender fairness over time.

User choice models have a lesser impact on fairness compared to ranking strategies.

Simulation results demonstrate the importance of algorithmic interventions for fairness.

Abstract

As recommender systems are prone to various biases, mitigation approaches are needed to ensure that recommendations are fair to various stakeholders. One particular concern in music recommendation is artist gender fairness. Recent work has shown that the gender imbalance in the sector translates to the output of music recommender systems, creating a feedback loop that can reinforce gender biases over time. In this work, we examine that feedback loop to study whether algorithmic strategies or user behavior are a greater contributor to ongoing improvement (or loss) in fairness as models are repeatedly re-trained on new user feedback data. We simulate user interaction and re-training to investigate the effects of ranking strategies and user choice models on gender fairness metrics. We find re-ranking strategies have a greater effect than user choice models on recommendation fairness over time.