{"title":"通过机器学习预测P2P借贷平台的失败:以中国为例","authors":"Jen-Yin Yeh, Hsin-Yu Chiu, Jhih-Huei Huang","doi":"arxiv-2311.14577","DOIUrl":null,"url":null,"abstract":"This study employs machine learning models to predict the failure of\nPeer-to-Peer (P2P) lending platforms, specifically in China. By employing the\nfilter method and wrapper method with forward selection and backward\nelimination, we establish a rigorous and practical procedure that ensures the\nrobustness and importance of variables in predicting platform failures. The\nresearch identifies a set of robust variables that consistently appear in the\nfeature subsets across different selection methods and models, suggesting their\nreliability and relevance in predicting platform failures. The study highlights\nthat reducing the number of variables in the feature subset leads to an\nincrease in the false acceptance rate while the performance metrics remain\nstable, with an AUC value of approximately 0.96 and an F1 score of around 0.88.\nThe findings of this research provide significant practical implications for\nregulatory authorities and investors operating in the Chinese P2P lending\nindustry.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":"47 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting Failure of P2P Lending Platforms through Machine Learning: The Case in China\",\"authors\":\"Jen-Yin Yeh, Hsin-Yu Chiu, Jhih-Huei Huang\",\"doi\":\"arxiv-2311.14577\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study employs machine learning models to predict the failure of\\nPeer-to-Peer (P2P) lending platforms, specifically in China. By employing the\\nfilter method and wrapper method with forward selection and backward\\nelimination, we establish a rigorous and practical procedure that ensures the\\nrobustness and importance of variables in predicting platform failures. The\\nresearch identifies a set of robust variables that consistently appear in the\\nfeature subsets across different selection methods and models, suggesting their\\nreliability and relevance in predicting platform failures. The study highlights\\nthat reducing the number of variables in the feature subset leads to an\\nincrease in the false acceptance rate while the performance metrics remain\\nstable, with an AUC value of approximately 0.96 and an F1 score of around 0.88.\\nThe findings of this research provide significant practical implications for\\nregulatory authorities and investors operating in the Chinese P2P lending\\nindustry.\",\"PeriodicalId\":501372,\"journal\":{\"name\":\"arXiv - QuantFin - General Finance\",\"volume\":\"47 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-11-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - General Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2311.14577\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - General Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2311.14577","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Predicting Failure of P2P Lending Platforms through Machine Learning: The Case in China
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.