Scholarlink

<p>This study aims to improve the prediction of borrower default risk in the peer-to-peer (P2P) lending sector by integrating machine learning techniques with feature selection strategies. Recursive Feature Elimination (RFE) is applied to enhance model transparency and predictive efficiency, addressing both computational and decision-related aspects of credit risk analysis. Using a real-world Lending Club dataset comprising 725,096 loan records, five machine learning models—Random Forest, Logistic Regression, Extreme Gradient Boosting, Multi-layer Perceptron, and K-Nearest Neighbors—were developed and fine-tuned via GridSearchCV. Model performance was assessed using accuracy, AUC, precision, recall, and F1-score. Among these, the Random Forest algorithm achieved the best performance with 91% accuracy and a 97% AUC. Key influential features included the debt-to-income ratio, last payment amount, and debt settlement indicator. The findings underscore the value of ensemble learning models in large-scale credit scoring and offer practical insights for P2P lending platforms and financial institutions to strengthen risk assessment, refine interest rate policies, and safeguard investor assets. This work presents a comprehensive, data-driven approach aligned with real-world financial risk management practices.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Data-driven prediction of borrower default in P2P lending using feature-optimized ML models

  • 期刊论文

  • 发表日期：

    2026年5月4日

查看全文
  • Alok Kumar Sharma,
  • Kuei-Chien Chiu

摘要

This study aims to improve the prediction of borrower default risk in the peer-to-peer (P2P) lending sector by integrating machine learning techniques with feature selection strategies. Recursive Feature Elimination (RFE) is applied to enhance model transparency and predictive efficiency, addressing both computational and decision-related aspects of credit risk analysis. Using a real-world Lending Club dataset comprising 725,096 loan records, five machine learning models—Random Forest, Logistic Regression, Extreme Gradient Boosting, Multi-layer Perceptron, and K-Nearest Neighbors—were developed and fine-tuned via GridSearchCV. Model performance was assessed using accuracy, AUC, precision, recall, and F1-score. Among these, the Random Forest algorithm achieved the best performance with 91% accuracy and a 97% AUC. Key influential features included the debt-to-income ratio, last payment amount, and debt settlement indicator. The findings underscore the value of ensemble learning models in large-scale credit scoring and offer practical insights for P2P lending platforms and financial institutions to strengthen risk assessment, refine interest rate policies, and safeguard investor assets. This work presents a comprehensive, data-driven approach aligned with real-world financial risk management practices.