Answers are grounded in this paper and cite their sources.
Recent studies have primarily focused on improving the predictive performance of models for credit card default prediction, whereas fairness across gender groups has received less attention. This study proposes a gender-aware framework for credit card default prediction to evaluate predictive performance and fairness across male and female borrowers. Five machine learning classifiers were evaluated on the full credit card default dataset and its male and female subsets. For each experimental scenario, three data balancing techniques were applied to address class imbalance. Classifier performance was assessed using five classification metrics, while gender fairness was evaluated using five fairness metrics. The results revealed differences in predictive performance between male and female borrowers; however, an additional equal-size sensitivity analysis indicated that the apparent female performance advantage was not consistently maintained after controlling for subgroup size and train–test split variability. The findings also highlight the trade-off between improving minority class prediction and limiting gender disparities in credit card default prediction.
No takes yet. Share an insight, caveat, or question.
Huthaifa Aljawazneh (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: