Predicting Failure of P2P Lending Platforms through Machine Learning: The Case in China

Paper: arXiv 2311.14577

Authors: Jen-Yin Yeh, Hsin-Yu Chiu, Jhih-Huei Huang

Abstract

This study employs machine learning models to predict the failure of Peer-to-Peer (P2P) lending platforms, specifically in China. By employing the filter method and wrapper method with forward selection and backward elimination, we establish a rigorous and practical procedure that ensures the robustness and importance of variables in predicting platform failures. The research identifies a set of robust variables that consistently appear in the feature subsets across different selection methods and models, suggesting their reliability and relevance in predicting platform failures. The study highlights that reducing the number of variables in the feature subset leads to an increase in the false acceptance rate while the performance metrics remain stable, with an AUC value of approximately 0.96 and an F1 score of around 0.88. The findings of this research provide significant practical implications for regulatory authorities and investors operating in the Chinese P2P lending industry.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 7.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper provides a strong empirical application of standard feature selection and classification algorithms to predict Chinese P2P platform defaults, yielding strong diagnostic metrics (AUC ~0.96). It relies primarily on applied machine learning workflows rather than novel theoretical derivations, making it highly practical but mathematically straightforward.

Research Flowchart

  flowchart TD
    A[Research Goal: Predict Chinese P2P Platform Failures] --> B[Data Collection: P2P Platform Financial & Operational Metrics]
    B --> C[Feature Selection: Filter Method & Wrapper Method]
    C --> D[Machine Learning Modeling & Variable Robustness Analysis]
    D --> E[Outcome 1: Highly Stable Performance<br>AUC ~0.96, F1 ~0.88]
    D --> F[Outcome 2: Robust Feature Subsets & Trade-off<br>Fewer Variables Increase False Acceptance Rate]
    E --> G[Practical Implications for Chinese Regulators & Investors]
    F --> G