In the RecSys ’24 Challenge, participants tackled news recommendations using a large-scale Danish dataset. Although the top-performing models achieved similar accuracy scores, they produced markedly different results on beyond-accuracy metrics, highlighting the need for further research into the normative alignment of recommender systems.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
References
Jannach, D. & Jugovac, M. ACM Trans. Manage. Inf. Syst. 10, 1–23 (2019).
Ferrari Dacrema, M., Cremonesi, P. & Jannach, D. In Proc. 13th ACM Conference on Recommender Systems 101–109 (ACM, 2019).
Vrijenhoek, S., et al. In Proc. 2021 Conference on Human Information Interaction and Retrieval 173–183 (ACM, 2021).
Elahi, M. et al. AI Ethics 2, 103–114 (2022).
Jannach, D., Pu, P., Ricci, F. & Zanker, M. Recommender Systems: Trends and Frontiers (John Wiley and Sons, 2022).
Kruse, J. et al. In Proc. 18th ACM Conference on Recommender Systems 1195–1199 (ACM, 2024).
Kruse, J. et al. In Proc. Recommender Systems Challenge 2024 1–11 (ACM, 2024).
Wu, F. et al. In Proc. 58th Annual Meeting of the Association for Computational Linguistics 3597–3606 (ACL, 2020).
Kaminskas, M. & Bridge, D. ACM Trans. Interact. Intell. Syst. 7, 1–42 (2016).
Zhou, G. et al. In Proc. 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 1059–1068 (ACM, 2018).
Acknowledgements
The authors acknowledge employers and funding bodies, including Ekstra Bladet, JP/Politikens Media Group, Technical University of Denmark, Copenhagen Business School, Innovation Foundation Denmark (grant number 1044-00058B), and the Platform Intelligence in News-Project (grant number 0175-00014B). They also thank the RecSys organization for the opportunity to co-host the competition, the RecSys Challenge co-chairs M. Polignano, C. Pomo and A. Srivastava, and A. Uppal for his valuable contributions throughout the competition.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Kruse, J., Lindskow, K., Andersen, M.R. et al. Why design choices matter in recommender systems. Nat Mach Intell 7, 979–980 (2025). https://doi.org/10.1038/s42256-025-01043-5
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1038/s42256-025-01043-5
