Automating Credit Card Limit Adjustments Using Machine Learning
This addresses the scalability issue for banks facing increasing credit card holders, but it is incremental as it applies existing methods to a specific domain problem.
The paper tackled automating credit card limit adjustments for Venezuelan banks by proposing a cost-sensitive machine learning model, which achieved almost perfect agreement with manual committee decisions as measured by Cohen's kappa coefficient.
Venezuelan banks have historically made credit card limit adjustment decisions manually through committees. However, since the number of credit card holders in Venezuela is expected to increase in the upcoming months due to economic improvements, manual decisions are starting to become unfeasible. In this project, a machine learning model that uses cost-sensitive learning is proposed to automate the task of handing out credit card limit increases. To accomplish this, several neural network and XGBoost models are trained and compared, leveraging Venezolano de Credito's data and using grid search with 10-fold cross-validation. The proposed model is ultimately chosen due to its superior balance of accuracy, cost-effectiveness, and interpretability. The model's performance is evaluated against the committee's decisions using Cohen's kappa coefficient, showing an almost perfect agreement.