Mostra: A Flexible Balancing Framework to Trade-off User, Artist and Platform Objectives for Music Sequencing

TL;DR

Mostra is a flexible framework that balances multiple objectives in music track sequencing, optimizing user satisfaction, artist exposure, and platform health through a novel transformer-based model with multi-objective decoding.

Contribution

The paper introduces Mostra, a novel Set Transformer-based architecture with submodular multi-objective beam search for dynamic trade-offs in music sequencing.

Findings

Effective balancing of multiple objectives demonstrated on real platform data

Superior performance in trade-off management compared to baseline methods

Insights into objective interactions and trade-offs in music recommendation

Abstract

We consider the task of sequencing tracks on music streaming platforms where the goal is to maximise not only user satisfaction, but also artist- and platform-centric objectives, needed to ensure long-term health and sustainability of the platform. Grounding the work across four objectives: Sat, Discovery, Exposure and Boost, we highlight the need and the potential to trade-off performance across these objectives, and propose Mostra, a Set Transformer-based encoder-decoder architecture equipped with submodular multi-objective beam search decoding. The proposed model affords system designers the power to balance multiple goals, and dynamically control the impact on one objective to satisfy other objectives. Through extensive experiments on data from a large-scale music streaming platform, we present insights on the trade-offs that exist across different objectives, and demonstrate that the proposed framework leads to a superior, just-in-time balancing across the various metrics of interest.