August 13, 2025Deleted JournalOpen Access

Effectiveness Evaluation of Big Data Risk Control Models in Consumer Credit: A Comparative Study of Default Prediction Based on XGBoost Algorithm

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Comparative study of XGBoost and traditional models reveals significant improvements in credit risk prediction accuracy.

The XGBoost model achieved a 97% accuracy rate on consumer credit risk prediction, outperforming traditional models.
With a true positive rate of 86.04%, the XGBoost model demonstrates considerable effectiveness in identifying credit defaults.
This observational analysis employed a dataset of 168,000 records, comparing performance against logistic regression and other models.
The findings suggest that effective risk control strategies are essential for balancing credit risk and business efficiency.

Jintao Lv (2025) studied this question.

View Full Paper

Ask AI

Bookmark