Explainable Deep Reinforcement Learning for Dynamic Credit Limit Adjustment

Abstract

In the ever-evolving financial landscape, dynamic credit limit adjustment plays a critical role in optimizing customer experience and risk management. Traditional methods often rely on static, rule-based systems that lack adaptability and transparency. This paper proposes an Explainable Deep Reinforcement Learning (XDRL) framework to automate and personalize credit limit adjustments based on customer behavior, financial data, and macroeconomic indicators. Our model learns optimal credit limit strategies that balance risk, customer satisfaction, and profitability. To ensure transparency and regulatory compliance, we integrate explainability modules—such as SHAP values and attention mechanisms—into the DRL pipeline. We evaluate the system on real-world or simulated credit data, demonstrating improvements in credit utilization, default prediction, and interpretability. This work paves the way for safer, more accountable AI-driven decision-making in the credit industry.