Gender airness in achine earning odels for redit ard efault rediction

Abstract 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.

Authors

Institutions

Publication Details

Journal
Discover Global Society
Published
2026-11-16
DOI
https://doi.org/10.1007/s44282-026-00647-5
Primary Topic
Financial Distress and Bankruptcy Prediction
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Gender airness in achine earning odels for redit ard efault rediction

Huthaifa Aljawazneh
1 links
Discover Global Society
Financial Distress and Bankruptcy Prediction
article

Gender airness in achine earning odels for redit ard efault rediction

Huthaifa Aljawazneh
article en

Abstract

Abstract 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.

Discover Global SocietyVol. 4(1)
Al-Zaytoonah University of Jordan (JO)
Reduced inequalities, Gender equality
Financial Distress and Bankruptcy Prediction
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon