{"title":"机器的崛起:机器学习在抵押贷款提前支付建模中的应用","authors":"Glenn M. Schultz, F. Fabozzi","doi":"10.3905/jfi.2021.1.123","DOIUrl":null,"url":null,"abstract":"Key to the valuation of agency residential mortgage-backed securities (MBSs) is the modeling of voluntary prepayment and default behaviors of the underlying borrowers in the mortgage pool. The proliferation of pool- and loan-level data coupled with access to advanced machine learning algorithms has opened the door to the application of machine learning to mortgage prepayment modeling. The modular prepayment model, one that relies on defined functions to predict mortgage prepayment, has dominated the MBS market nearly since its inception. However, machine learning models are beginning to make inroads and, in some cases, are replacing traditional modular prepayment models. The modular and machine learning model differ in the following ways: In the case of modular prepayment models, either added or multiplicative, the modeler defines the functional form of each feature as well as the “tuning” of the parameters passed to each. Machine learning or “second generation” mortgage prepayment models differ in the sense that the modeler “tunes” the hyperparameters that determine the bias variance tradeoff while the machine determines the functional form of each feature of the model. In this article, the authors propose a machine learning mortgage prepayment model using a boosted gradient classifier, trained at the loan level and generalized to the pool level. A gradient boosted classifier is a tree-based model using an ensemble of weak learners to create a strong committee for prediction.","PeriodicalId":53711,"journal":{"name":"Journal of Fixed Income","volume":"31 1","pages":"6 - 19"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Rise of the Machines: Application of Machine Learning to Mortgage Prepayment Modeling\",\"authors\":\"Glenn M. Schultz, F. Fabozzi\",\"doi\":\"10.3905/jfi.2021.1.123\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Key to the valuation of agency residential mortgage-backed securities (MBSs) is the modeling of voluntary prepayment and default behaviors of the underlying borrowers in the mortgage pool. The proliferation of pool- and loan-level data coupled with access to advanced machine learning algorithms has opened the door to the application of machine learning to mortgage prepayment modeling. The modular prepayment model, one that relies on defined functions to predict mortgage prepayment, has dominated the MBS market nearly since its inception. However, machine learning models are beginning to make inroads and, in some cases, are replacing traditional modular prepayment models. The modular and machine learning model differ in the following ways: In the case of modular prepayment models, either added or multiplicative, the modeler defines the functional form of each feature as well as the “tuning” of the parameters passed to each. Machine learning or “second generation” mortgage prepayment models differ in the sense that the modeler “tunes” the hyperparameters that determine the bias variance tradeoff while the machine determines the functional form of each feature of the model. In this article, the authors propose a machine learning mortgage prepayment model using a boosted gradient classifier, trained at the loan level and generalized to the pool level. A gradient boosted classifier is a tree-based model using an ensemble of weak learners to create a strong committee for prediction.\",\"PeriodicalId\":53711,\"journal\":{\"name\":\"Journal of Fixed Income\",\"volume\":\"31 1\",\"pages\":\"6 - 19\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Fixed Income\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3905/jfi.2021.1.123\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Fixed Income","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3905/jfi.2021.1.123","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Rise of the Machines: Application of Machine Learning to Mortgage Prepayment Modeling
Key to the valuation of agency residential mortgage-backed securities (MBSs) is the modeling of voluntary prepayment and default behaviors of the underlying borrowers in the mortgage pool. The proliferation of pool- and loan-level data coupled with access to advanced machine learning algorithms has opened the door to the application of machine learning to mortgage prepayment modeling. The modular prepayment model, one that relies on defined functions to predict mortgage prepayment, has dominated the MBS market nearly since its inception. However, machine learning models are beginning to make inroads and, in some cases, are replacing traditional modular prepayment models. The modular and machine learning model differ in the following ways: In the case of modular prepayment models, either added or multiplicative, the modeler defines the functional form of each feature as well as the “tuning” of the parameters passed to each. Machine learning or “second generation” mortgage prepayment models differ in the sense that the modeler “tunes” the hyperparameters that determine the bias variance tradeoff while the machine determines the functional form of each feature of the model. In this article, the authors propose a machine learning mortgage prepayment model using a boosted gradient classifier, trained at the loan level and generalized to the pool level. A gradient boosted classifier is a tree-based model using an ensemble of weak learners to create a strong committee for prediction.
期刊介绍:
The Journal of Fixed Income (JFI) provides sophisticated analytical research and case studies on bond instruments of all types – investment grade, high-yield, municipals, ABSs and MBSs, and structured products like CDOs and credit derivatives. Industry experts offer detailed models and analysis on fixed income structuring, performance tracking, and risk management. JFI keeps you on the front line of fixed income practices by: •Staying current on the cutting edge of fixed income markets •Managing your bond portfolios more efficiently •Evaluating interest rate strategies and manage interest rate risk •Gaining insights into the risk profile of structured products.