Leonardo Gambacorta , Yiping Huang , Han Qiu , Jingyi Wang
{"title":"机器学习和非传统数据如何影响信用评分?来自一家中国金融科技公司的新证据","authors":"Leonardo Gambacorta , Yiping Huang , Han Qiu , Jingyi Wang","doi":"10.1016/j.jfs.2024.101284","DOIUrl":null,"url":null,"abstract":"<div><p>This paper compares the predictive power of credit scoring models based on machine learning techniques with that of traditional loss and default models. Using proprietary transaction-level data from a leading fintech company in China, we test the performance of different models to predict losses and defaults both in normal times and when the economy is subject to a shock. In particular, we analyse the case of an (exogenous) change in regulation policy on shadow banking in China that caused credit conditions to deteriorate. We find that the model based on machine learning and non-traditional data is better able to predict losses and defaults than traditional models in the presence of a negative shock to the aggregate credit supply. This result reflects a higher capacity of non-traditional data to capture relevant borrower characteristics and of machine learning techniques to better mine the non-linear relationship between variables in a period of stress.</p></div>","PeriodicalId":48027,"journal":{"name":"Journal of Financial Stability","volume":"73 ","pages":"Article 101284"},"PeriodicalIF":6.1000,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm\",\"authors\":\"Leonardo Gambacorta , Yiping Huang , Han Qiu , Jingyi Wang\",\"doi\":\"10.1016/j.jfs.2024.101284\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>This paper compares the predictive power of credit scoring models based on machine learning techniques with that of traditional loss and default models. Using proprietary transaction-level data from a leading fintech company in China, we test the performance of different models to predict losses and defaults both in normal times and when the economy is subject to a shock. In particular, we analyse the case of an (exogenous) change in regulation policy on shadow banking in China that caused credit conditions to deteriorate. We find that the model based on machine learning and non-traditional data is better able to predict losses and defaults than traditional models in the presence of a negative shock to the aggregate credit supply. This result reflects a higher capacity of non-traditional data to capture relevant borrower characteristics and of machine learning techniques to better mine the non-linear relationship between variables in a period of stress.</p></div>\",\"PeriodicalId\":48027,\"journal\":{\"name\":\"Journal of Financial Stability\",\"volume\":\"73 \",\"pages\":\"Article 101284\"},\"PeriodicalIF\":6.1000,\"publicationDate\":\"2024-06-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Financial Stability\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S157230892400069X\",\"RegionNum\":2,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BUSINESS, FINANCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Financial Stability","FirstCategoryId":"96","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S157230892400069X","RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm
This paper compares the predictive power of credit scoring models based on machine learning techniques with that of traditional loss and default models. Using proprietary transaction-level data from a leading fintech company in China, we test the performance of different models to predict losses and defaults both in normal times and when the economy is subject to a shock. In particular, we analyse the case of an (exogenous) change in regulation policy on shadow banking in China that caused credit conditions to deteriorate. We find that the model based on machine learning and non-traditional data is better able to predict losses and defaults than traditional models in the presence of a negative shock to the aggregate credit supply. This result reflects a higher capacity of non-traditional data to capture relevant borrower characteristics and of machine learning techniques to better mine the non-linear relationship between variables in a period of stress.
期刊介绍:
The Journal of Financial Stability provides an international forum for rigorous theoretical and empirical macro and micro economic and financial analysis of the causes, management, resolution and preventions of financial crises, including banking, securities market, payments and currency crises. The primary focus is on applied research that would be useful in affecting public policy with respect to financial stability. Thus, the Journal seeks to promote interaction among researchers, policy-makers and practitioners to identify potential risks to financial stability and develop means for preventing, mitigating or managing these risks both within and across countries.