Financial content ranking balances fairness and engagement using reinforcement learning
FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization
Machine LearningArtificial IntelligenceInformation Retrieval
Summary
Financial services need to show a variety of products fairly to users, not just the most popular ones, to meet rules and avoid concentrating attention. The authors treat this fair showing of content like a game where an AI learns the best way to order items while respecting fairness rules. They also factor in how uncertain the AI is about predicting which items users will click on, allowing it to make bigger changes when predictions are less sure. Their method, called FARE, works with any existing click prediction system and improves fairness without hurting overall user interest too much.
What this means in practice
- •For online financial services: Implement fair product rankings that balance exposure mandates with user engagement in digital financial content platforms.$Commercial implications: Enables development of fairness-aware recommendation systems for financial platforms to meet regulatory requirements while maintaining revenue.
- •For advertising technology teams: Use uncertainty-aware reinforcement learning to optimize ad rankings under exposure share constraints, improving fairness without sacrificing clicks.
Authors
Arundeep Chinta, Lucas Vinh Tran, Jay Katukuri
Abstract
Content personalization systems in financial services must ensure fair exposure across diverse offerings-a requirement driven by contractual obligations and the need to prevent "rich-get-richer" dynamics where content with high click-through rate (CTR) dominates while other relevant products receive minimal visibility. Share of Voice (SOV) constraints, which guarantee each content category a target fraction of top-position exposure, address this by promoting product diversity and balanced user discovery. While re-ranking layers atop CTR models are common in practice, we propose two key novelties: (1) framing SOV-constrained ranking as a deep reinforcement learning problem analogous to constrained trade execution in algorithmic finance, and (2) explicitly incorporating CTR prediction uncertainty into the agent's state space and policy design-enabling larger ranking adjustments for high-uncertainty predictions where deviation from CTR-optimal ordering is less costly. We introduce FARE (Fair Ranking Executor), a modular uncertainty-aware execution layer that translates any black-box CTR model's predictions into SOV-fair rankings without retraining the underlying model. Our uncertainty-weighted proportional control policy (FARE-PC) and learned neural policies (FARE-ES, FARE-PPO) demonstrate that uncertainty-aware approaches can substantially reduce SOV deviation from fairness targets while minimizing engagement loss, with gradient-free evolution strategies outperforming policy gradient methods on synthetic data and the ordering reversing on KuaiRand-Pure.