An Integrated Machine Learning and Deep Learning Framework for Credit Card Approval Prediction

TL;DR

This work tackles credit card approval prediction under data imbalance and high dimensionality by proposing an integrated ML and DL framework that ensembles multiple base models with a neural network. The pipeline emphasizes comprehensive preprocessing, feature engineering (including interaction, polynomial, and temporal features), SMOTE balancing, and Optuna-driven hyperparameter tuning, coupled with a stacking ensemble and neural-embedding fusion. Empirical results show the NN+Ensemble approach achieving superior precision, recall, F1-score, AUC, and Cohen’s Kappa compared with traditional single-model baselines, demonstrating improved predictive reliability. The framework offers a scalable, robust solution for financial decision-making in credit risk assessment, with potential for real-time applications.

Abstract

Credit scoring is vital in the financial industry, assessing the risk of lending to credit card applicants. Traditional credit scoring methods face challenges with large datasets and data imbalance between creditworthy and non-creditworthy applicants. This paper introduces an advanced machine learning and deep learning framework to improve the accuracy and reliability of credit card approval predictions. We utilized extensive datasets of user application records and credit history, implementing a comprehensive preprocessing strategy, feature engineering, and model integration. Our methodology combines neural networks with an ensemble of base models, including logistic regression, support vector machines, k-nearest neighbors, decision trees, random forests, and gradient boosting. The ensemble approach addresses data imbalance using Synthetic Minority Over-sampling Technique (SMOTE) and mitigates overfitting risks. Experimental results show that our integrated model surpasses traditional single-model approaches in precision, recall, F1-score, AUC, and Kappa, providing a robust and scalable solution for credit card approval predictions. This research underscores the potential of advanced machine learning techniques to transform credit risk assessment and financial decision-making.

Figures (7)

• Figure 1: Comparison of customer characteristics by gender and asset ownership.
• Figure 2: Loan status trends by income type and gender.
• Figure 3: Loan status distribution by housing type.
• Figure 4: Heatmap for Missing values
• Figure 5: Distribution of features