What type of study is this?

Vehicle Loan Default Prediction Based on Machine Learning

View Full Paper

Ask AI

Bookmark

XGBoost achieved an AUC of 0.89, significantly outperforming logistic regression with AUC of 0.62.
Key risk factors identified include credit score, loan-to-value ratio over 85%, and self-employed status.
Feature engineering methods like SMOTE and outlier correction improved data quality for loan prediction models.
Findings suggest actionable insights for financial institutions to refine lending policies and mitigate losses.

No takes yet. Share an insight, caveat, or question.

Comparison of XGBoost and LightGBM reveals dynamic tools for loan default prediction, indicating improved policies.

Xiaohui Wu (2025) studied this question.

View Full Paper

Ask AI

Bookmark