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.
Originalsprog | Engelsk |
---|---|
Titel | WWW 2022 - Proceedings of the ACM Web Conference 2022 |
Forlag | Association for Computing Machinery, Inc. |
Publikationsdato | 2022 |
Sider | 2936-2945 |
ISBN (Elektronisk) | 9781450390965 |
DOI | |
Status | Udgivet - 2022 |
Begivenhed | 31st ACM World Wide Web Conference, WWW 2022 - Virtual, Online, Frankrig Varighed: 25 apr. 2022 → 29 apr. 2022 |
Konference
Konference | 31st ACM World Wide Web Conference, WWW 2022 |
---|---|
Land/Område | Frankrig |
By | Virtual, Online |
Periode | 25/04/2022 → 29/04/2022 |
Sponsor | ACM SIGWEB |
Bibliografisk note
Funding Information:The work is supported by the National Natural Science Foundation of China (61872214).
Publisher Copyright:
© 2022 ACM.