Fraud-Proof Revenue Division on Subscription Platforms

2025-11-06

AI Summary

This paper addresses revenue allocation imbalance in subscription-based platforms caused by collusive fraud between users and creators. We propose a mechanism-design-driven, manipulation-resistant solution. First, we formalize three manipulation-resistance axioms, exposing fundamental incentive-incompatibility flaws in prevalent proportional allocation rules. Building on this analysis, we design ScaledUserProp—a novel allocation mechanism that eliminates fraudulent incentives at their source. Our approach integrates mechanism design theory with computational complexity analysis and conducts empirical evaluation on both real-world and synthetic streaming datasets. Results demonstrate that ScaledUserProp achieves superior manipulation resistance while preserving fairness, outperforming existing allocation rules across all key metrics. Crucially, it requires no machine learning–based fraud detection models, ensuring full interpretability and practical deployability.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

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.

Problem

• Developing fraud-resistant revenue division mechanisms for subscription platforms
• Analyzing manipulation-resistance axioms to prevent fraudulent creator behavior
• Proposing ScaledUserProp as a fair alternative to existing flawed systems

Innovation

• Introduces fraud-resistant revenue division mechanisms
• Proposes ScaledUserProp satisfying three manipulation-resistance axioms
• Validates fairness with real-world and synthetic streaming data