Interpolating Item and User Fairness in Multi-Sided Recommendations
This addresses fairness for platforms, sellers, and customers in multi-sided recommendations, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of balancing multiple stakeholder interests in algorithmic recommendations by introducing a fair recommendation framework, FAIR, and a low-regret algorithm, FORM, for dynamic online settings, demonstrating efficacy in maintaining platform revenue while ensuring fairness for items and users through theoretical analysis and a real-world case study.
Today's online platforms heavily lean on algorithmic recommendations for bolstering user engagement and driving revenue. However, these recommendations can impact multiple stakeholders simultaneously -- the platform, items (sellers), and users (customers) -- each with their unique objectives, making it difficult to find the right middle ground that accommodates all stakeholders. To address this, we introduce a novel fair recommendation framework, Problem (FAIR), that flexibly balances multi-stakeholder interests via a constrained optimization formulation. We next explore Problem (FAIR) in a dynamic online setting where data uncertainty further adds complexity, and propose a low-regret algorithm FORM that concurrently performs real-time learning and fair recommendations, two tasks that are often at odds. Via both theoretical analysis and a numerical case study on real-world data, we demonstrate the efficacy of our framework and method in maintaining platform revenue while ensuring desired levels of fairness for both items and users.