Optimizing credit limit adjustments under adversarial goals using reinforcement learning

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

Abstract: Highlights•We use reinforcement learning for deciding whether to increase credit card limits.•We created a business simulator for off-line training of the model.•The resulting model can be implemented by both fintechs and traditional banks.•We reveal the most important features in the simulator model with Shapley values.