{"title":"企业违约风险的机器学习:多期预测、脆弱性相关性、贷款组合和尾部概率","authors":"Fabio Sigrist, N. Leuenberger","doi":"10.2139/ssrn.3938972","DOIUrl":null,"url":null,"abstract":"We use machine learning methods for modeling multi-period corporate default probabilities and obtain higher prediction accuracy compared to linear models with the differences being larger for longer prediction horizons. Overall, tree-boosting has the highest prediction accuracy. In addition, we introduce a novel hybrid econometric-machine learning model combining tree-boosting with a latent frailty model. This ``LaGaBoost frailty model\" results in more accurate predictions of upper tails of portfolio losses compared to both a linear frailty model and machine learning methods ignoring frailty correlation. We also investigate the reasons and find various explanations for the observed differences in prediction accuracy.","PeriodicalId":331807,"journal":{"name":"Banking & Insurance eJournal","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Machine Learning for Corporate Default Risk: Multi-Period Prediction, Frailty Correlation, Loan Portfolios, and Tail Probabilities\",\"authors\":\"Fabio Sigrist, N. Leuenberger\",\"doi\":\"10.2139/ssrn.3938972\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We use machine learning methods for modeling multi-period corporate default probabilities and obtain higher prediction accuracy compared to linear models with the differences being larger for longer prediction horizons. Overall, tree-boosting has the highest prediction accuracy. In addition, we introduce a novel hybrid econometric-machine learning model combining tree-boosting with a latent frailty model. This ``LaGaBoost frailty model\\\" results in more accurate predictions of upper tails of portfolio losses compared to both a linear frailty model and machine learning methods ignoring frailty correlation. We also investigate the reasons and find various explanations for the observed differences in prediction accuracy.\",\"PeriodicalId\":331807,\"journal\":{\"name\":\"Banking & Insurance eJournal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-10-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Banking & Insurance eJournal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2139/ssrn.3938972\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Banking & Insurance eJournal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2139/ssrn.3938972","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Machine Learning for Corporate Default Risk: Multi-Period Prediction, Frailty Correlation, Loan Portfolios, and Tail Probabilities
We use machine learning methods for modeling multi-period corporate default probabilities and obtain higher prediction accuracy compared to linear models with the differences being larger for longer prediction horizons. Overall, tree-boosting has the highest prediction accuracy. In addition, we introduce a novel hybrid econometric-machine learning model combining tree-boosting with a latent frailty model. This ``LaGaBoost frailty model" results in more accurate predictions of upper tails of portfolio losses compared to both a linear frailty model and machine learning methods ignoring frailty correlation. We also investigate the reasons and find various explanations for the observed differences in prediction accuracy.