{"title":"回报预测中的复杂性美德","authors":"BRYAN KELLY, SEMYON MALAMUD, KANGYING ZHOU","doi":"10.1111/jofi.13298","DOIUrl":null,"url":null,"abstract":"<p>Much of the extant literature predicts market returns with “simple” models that use only a few parameters. Contrary to conventional wisdom, we theoretically prove that simple models severely understate return predictability compared to “complex” models in which the number of parameters exceeds the number of observations. We empirically document the virtue of complexity in U.S. equity market return prediction. Our findings establish the rationale for modeling expected returns through machine learning.</p>","PeriodicalId":15753,"journal":{"name":"Journal of Finance","volume":null,"pages":null},"PeriodicalIF":7.6000,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jofi.13298","citationCount":"0","resultStr":"{\"title\":\"The Virtue of Complexity in Return Prediction\",\"authors\":\"BRYAN KELLY, SEMYON MALAMUD, KANGYING ZHOU\",\"doi\":\"10.1111/jofi.13298\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Much of the extant literature predicts market returns with “simple” models that use only a few parameters. Contrary to conventional wisdom, we theoretically prove that simple models severely understate return predictability compared to “complex” models in which the number of parameters exceeds the number of observations. We empirically document the virtue of complexity in U.S. equity market return prediction. Our findings establish the rationale for modeling expected returns through machine learning.</p>\",\"PeriodicalId\":15753,\"journal\":{\"name\":\"Journal of Finance\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":7.6000,\"publicationDate\":\"2023-12-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jofi.13298\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Finance\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/jofi.13298\",\"RegionNum\":1,\"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 Finance","FirstCategoryId":"96","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jofi.13298","RegionNum":1,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
Much of the extant literature predicts market returns with “simple” models that use only a few parameters. Contrary to conventional wisdom, we theoretically prove that simple models severely understate return predictability compared to “complex” models in which the number of parameters exceeds the number of observations. We empirically document the virtue of complexity in U.S. equity market return prediction. Our findings establish the rationale for modeling expected returns through machine learning.
期刊介绍:
The Journal of Finance is a renowned publication that disseminates cutting-edge research across all major fields of financial inquiry. Widely regarded as the most cited academic journal in finance, each issue reaches over 8,000 academics, finance professionals, libraries, government entities, and financial institutions worldwide. Published bi-monthly, the journal serves as the official publication of The American Finance Association, the premier academic organization dedicated to advancing knowledge and understanding in financial economics. Join us in exploring the forefront of financial research and scholarship.