How Bad is Top-$K$ Recommendation under Competing Content Creators?

Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang, Haifeng Xu
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39674-39701, 2023.

Abstract

This study explores the impact of content creators’ competition on user welfare in recommendation platforms, as well as the long-term dynamics of relevance-driven recommendations. We establish a model of creator competition, under the setting where the platform uses a top-$K$ recommendation policy, user decisions are guided by the Random Utility model, and creators, in absence of explicit utility functions, employ arbitrary no-regret learning algorithms for strategy updates. We study the user welfare guarantee through the lens of Price of Anarchy and show that the fraction of user welfare loss due to creator competition is always upper bounded by a small constant depending on $K$ and randomness in user decisions; we also prove the tightness of this bound. Our result discloses an intrinsic merit of the relevance-driven recommendation policy, as long as users’ decisions involve randomness and the platform provides reasonably many alternatives to its users.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-yao23b, title = {How Bad is Top-$K$ Recommendation under Competing Content Creators?}, author = {Yao, Fan and Li, Chuanhao and Nekipelov, Denis and Wang, Hongning and Xu, Haifeng}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {39674--39701}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/yao23b/yao23b.pdf}, url = {https://proceedings.mlr.press/v202/yao23b.html}, abstract = {This study explores the impact of content creators’ competition on user welfare in recommendation platforms, as well as the long-term dynamics of relevance-driven recommendations. We establish a model of creator competition, under the setting where the platform uses a top-$K$ recommendation policy, user decisions are guided by the Random Utility model, and creators, in absence of explicit utility functions, employ arbitrary no-regret learning algorithms for strategy updates. We study the user welfare guarantee through the lens of Price of Anarchy and show that the fraction of user welfare loss due to creator competition is always upper bounded by a small constant depending on $K$ and randomness in user decisions; we also prove the tightness of this bound. Our result discloses an intrinsic merit of the relevance-driven recommendation policy, as long as users’ decisions involve randomness and the platform provides reasonably many alternatives to its users.} }
Endnote
%0 Conference Paper %T How Bad is Top-$K$ Recommendation under Competing Content Creators? %A Fan Yao %A Chuanhao Li %A Denis Nekipelov %A Hongning Wang %A Haifeng Xu %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-yao23b %I PMLR %P 39674--39701 %U https://proceedings.mlr.press/v202/yao23b.html %V 202 %X This study explores the impact of content creators’ competition on user welfare in recommendation platforms, as well as the long-term dynamics of relevance-driven recommendations. We establish a model of creator competition, under the setting where the platform uses a top-$K$ recommendation policy, user decisions are guided by the Random Utility model, and creators, in absence of explicit utility functions, employ arbitrary no-regret learning algorithms for strategy updates. We study the user welfare guarantee through the lens of Price of Anarchy and show that the fraction of user welfare loss due to creator competition is always upper bounded by a small constant depending on $K$ and randomness in user decisions; we also prove the tightness of this bound. Our result discloses an intrinsic merit of the relevance-driven recommendation policy, as long as users’ decisions involve randomness and the platform provides reasonably many alternatives to its users.
APA
Yao, F., Li, C., Nekipelov, D., Wang, H. & Xu, H.. (2023). How Bad is Top-$K$ Recommendation under Competing Content Creators?. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:39674-39701 Available from https://proceedings.mlr.press/v202/yao23b.html.

Related Material