Paper: arXiv 2306.15585

Authors: Sherly Alfonso-Sánchez, Jesús Solano, Alejandro Correa-Bahnsen, Kristina P. Sendova, Cristián Bravo

Abstract

Reinforcement learning has been explored for many problems, from video games with deterministic environments to portfolio and operations management in which scenarios are stochastic; however, there have been few attempts to test these methods in banking problems. In this study, we sought to find and automatize an optimal credit card limit adjustment policy by employing reinforcement learning techniques. Because of the historical data available, we considered two possible actions per customer, namely increasing or maintaining an individual’s current credit limit. To find this policy, we first formulated this decision-making question as an optimization problem in which the expected profit was maximized; therefore, we balanced two adversarial goals: maximizing the portfolio’s revenue and minimizing the portfolio’s provisions. Second, given the particularities of our problem, we used an offline learning strategy to simulate the impact of the action based on historical data from a super-app in Latin America to train our reinforcement learning agent. Our results, based on the proposed methodology involving synthetic experimentation, show that a Double Q-learning agent with optimized hyperparameters can outperform other strategies and generate a non-trivial optimal policy not only reflecting the complex nature of this decision but offering an incentive to explore reinforcement learning in real-world banking scenarios. Our research establishes a conceptual structure for applying reinforcement learning framework to credit limit adjustment, presenting an objective technique to make these decisions primarily based on data-driven methods rather than relying only on expert-driven systems. We also study the use of alternative data for the problem of balance prediction, as the latter is a requirement of our proposed model. We find the use of such data does not always bring prediction gains.

Complexity vs Empirical Score

  • Math Complexity: 5.5/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper presents a novel application of offline Double Q-learning to retail banking credit limit optimization, effectively balancing revenue maximization and provision minimization. While it relies partly on synthetic experimentation alongside real super-app data from Latin America, the methodology is mathematically sound and addresses a real-world financial decision-making problem.

Research Flowchart

  flowchart TD
    A[Goal: Automate Optimal Credit Limit Policy<br>Maximize Revenue vs. Minimize Provisions] --> B[Data Inputs: Latin America Super-App<br>Historical Data & Alternative Data]
    B --> C[Formulate Optimization Problem &<br>Evaluate Balance Prediction Models]
    C --> D[Train Double Q-Learning Agent<br>Using Offline Learning Strategy]
    D --> E[Key Findings: Double Q-Learning Outperforms<br>Baselines & Generates Non-Trivial Policy]
    E --> F[Outcome: Data-Driven Framework Replaces<br>Expert-Driven Systems; Alt Data Shows Mixed Gains]