Recommending Podcasts for Cold-Start Users Based on Music Listening and Taste

TL;DR

This paper explores using music listening data to improve podcast recommendations for new users, addressing the cold-start problem with significant performance gains demonstrated through experiments.

Contribution

It introduces a novel approach leveraging music consumption behavior to enhance podcast recommendations for cold-start users, with extensive analysis of bias and model performance.

Findings

Up to 50% increase in recommendation accuracy

Effective use of music data for cold-start scenarios

Analysis of bias introduced by music-based features

Abstract

Recommender systems are increasingly used to predict and serve content that aligns with user taste, yet the task of matching new users with relevant content remains a challenge. We consider podcasting to be an emerging medium with rapid growth in adoption, and discuss challenges that arise when applying traditional recommendation approaches to address the cold-start problem. Using music consumption behavior, we examine two main techniques in inferring Spotify users preferences over more than 200k podcasts. Our results show significant improvements in consumption of up to 50\% for both offline and online experiments. We provide extensive analysis on model performance and examine the degree to which music data as an input source introduces bias in recommendations.