Fraud-Proof Revenue Division on Subscription Platforms

Abheek Ghosh, Tzeh Yuan Neoh, Nicholas Teh, Giannis Tyrovolas
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19426-19436, 2025.

Abstract

We study a model of subscription-based platforms where users pay a fixed fee for unlimited access to content, and creators receive a share of the revenue. Existing approaches to detecting fraud predominantly rely on machine learning methods, engaging in an ongoing arms race with bad actors. We explore revenue division mechanisms that inherently disincentivize manipulation. We formalize three types of manipulation-resistance axioms and examine which existing rules satisfy these. We show that a mechanism widely used by streaming platforms, not only fails to prevent fraud, but also makes detecting manipulation computationally intractable. We also introduce a novel rule, ScaledUserProp, that satisfies all three manipulation-resistance axioms. Finally, experiments with both real-world and synthetic streaming data support ScaledUserProp as a fairer alternative compared to existing rules.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-ghosh25d, title = {Fraud-Proof Revenue Division on Subscription Platforms}, author = {Ghosh, Abheek and Neoh, Tzeh Yuan and Teh, Nicholas and Tyrovolas, Giannis}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {19426--19436}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/ghosh25d/ghosh25d.pdf}, url = {https://proceedings.mlr.press/v267/ghosh25d.html}, abstract = {We study a model of subscription-based platforms where users pay a fixed fee for unlimited access to content, and creators receive a share of the revenue. Existing approaches to detecting fraud predominantly rely on machine learning methods, engaging in an ongoing arms race with bad actors. We explore revenue division mechanisms that inherently disincentivize manipulation. We formalize three types of manipulation-resistance axioms and examine which existing rules satisfy these. We show that a mechanism widely used by streaming platforms, not only fails to prevent fraud, but also makes detecting manipulation computationally intractable. We also introduce a novel rule, ScaledUserProp, that satisfies all three manipulation-resistance axioms. Finally, experiments with both real-world and synthetic streaming data support ScaledUserProp as a fairer alternative compared to existing rules.} }
Endnote
%0 Conference Paper %T Fraud-Proof Revenue Division on Subscription Platforms %A Abheek Ghosh %A Tzeh Yuan Neoh %A Nicholas Teh %A Giannis Tyrovolas %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-ghosh25d %I PMLR %P 19426--19436 %U https://proceedings.mlr.press/v267/ghosh25d.html %V 267 %X We study a model of subscription-based platforms where users pay a fixed fee for unlimited access to content, and creators receive a share of the revenue. Existing approaches to detecting fraud predominantly rely on machine learning methods, engaging in an ongoing arms race with bad actors. We explore revenue division mechanisms that inherently disincentivize manipulation. We formalize three types of manipulation-resistance axioms and examine which existing rules satisfy these. We show that a mechanism widely used by streaming platforms, not only fails to prevent fraud, but also makes detecting manipulation computationally intractable. We also introduce a novel rule, ScaledUserProp, that satisfies all three manipulation-resistance axioms. Finally, experiments with both real-world and synthetic streaming data support ScaledUserProp as a fairer alternative compared to existing rules.
APA
Ghosh, A., Neoh, T.Y., Teh, N. & Tyrovolas, G.. (2025). Fraud-Proof Revenue Division on Subscription Platforms. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:19426-19436 Available from https://proceedings.mlr.press/v267/ghosh25d.html.

Related Material