[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117342-en":3,"doc-seo-117342-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117342,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Enhancing real estate investment trust return forecasts using machine learning","The study extends machine learning empirical asset pricing by examining a comprehensive set of return-predicting signals for real estate investment trusts (REITs). Machine learning models outperform traditional ordinary least squares approaches, delivering measurable economic gains to REIT investors when forecasts are implemented. The analysis shows that REIT returns are more predictable than stock returns, and that this elevated predictability remains stable across time and across different industries, supporting practical use in real estate markets.","DOI: 10.1111/1540-6229.12527  \nORIGINAL ARTICLE  \nEnhancing real estate investment trust return forecasts using machine learning  \nKahshin Leow   Thies Lindenthal   \nDepartment of Land Economy, University of Cambridge, Cambridge, UK  \nCorrespondence  \nKahshin Leow, University of Cambridge, 17 Mill Lane, Cambridge CB2 1RX, UK. [Email: kahshin.leow@kings.cam.ac.uk](Email: kahshin.leow@kings.cam.ac.uk)  \nAbstract  \nWe extend the emerging literature on machine learning empirical asset pricing by analyzing a comprehensive set of return prediction factors for real estate investment trusts (REITs) . We show that machine learning models are superior to traditional ordinary least squares models and find that REIT investors experience significant economic gains when using machine learning forecasts. In particular, we show that REITs are more predictable than stocks and that their higher predictability is stable over time and across industries.  \n1  INTRODUCTION  \nIn this study, we build on the pioneering work of Gu et al. (2020), who combine a broad repertoire of machine learning methods with modern empirical asset pricing research to understand the dynamics of market risk premia for US stock returns. Their results suggest that machine learning improves the description of expected returns. They find that portfolio performance improves most prominently among the more sophisticated machine learning models due in large part to the nonlinear predictor interactions missed by simpler methods. Researchers have replicated Gu et al.’s (2020) work in several specific contexts. For example, Bianchi et al. (2021) employ machine learning methods to predict US Treasury bond returns and find strong statistical evidence in favor of extreme trees and neural networks. Leippold et al. (2022) add to the burgeoning financial machine learning literature by expanding previous findings to China, where they find that the predictability of the Chinese stock market is a fewfold higher than that of the US stock market (Gu et al., 2020) . Nonetheless, researchers have yet to apply the latest machine learning techniques to real estate  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2025 The Author(s) . Real Estate Economics published by Wiley Periodicals LLC on behalf of American Real Estate and Urban Economics Association.  \ninvestment trusts (REITs). Given the fundamental differences between stocks and real estate, such research is warranted.  \nOur study is motivated by two questions. First, do the findings of Gu et al. (2020), Bianchi et al.(2021), and Leippold et al. (2022) apply to the real estate market? If so, machine learning could aid in solving practical problems such as market timing, portfolio choice, and risk management, justifying its role in public real estate markets.  \nSecond, given the fundamental underlying differences between stocks and real estate, are there differences in the predictability of stock and real estate returns? One hypothesis is that the larger heterogeneity in the stock market makes it a more natural candidate for machine learning techniques than REITs. Another hypothesis cited by Nelling and Gyourko (1998), who find that REITshave lower predictability than stock returns, is that the REIT market has a smaller sample of firms than the general stock market, a numerical difference that has only increased since 1998 .  \nWe conduct a large-scale empirical analysis investigating 486 REITs over 1990–2021 . Our predictor set includes 94 firm-level characteristics for each REIT, the interactions of each characteristic with eight macroeconomic time series variables, and 17 sector dummy variables, totaling 863 baseline signals. Our benchmark ordinary least squares (OLS) regression models using only size and the book-to-market ratio as predictors (OLS-2) and size, the book-to-market ra","cbCaignxioo867HK","https://ap.wps.com/l/cbCaignxioo867HK","pdf",1893214,1,33,"English","en",105,"# Introduction\n## Motivation and research questions\n## Data and predictor set\n## Baseline and linear benchmark models\n## Regularization and dimension-reduction approaches\n## Nonlinear machine learning models\n## Cross-asset comparison: REITs vs stocks","[{\"question\":\"How do machine learning models compare with ordinary least squares for REIT return forecasting?\",\"answer\":\"Machine learning models provide superior out-of-sample forecasting relative to ordinary least squares models. The study reports improved performance across multiple model families.\"},{\"question\":\"What evidence indicates that machine learning forecasts generate economic gains for REIT investors?\",\"answer\":\"The study links improved predictive performance to significant economic gains when using machine learning forecasts. Better out-of-sample R2 translates into more favorable investor outcomes.\"},{\"question\":\"Are REIT returns more predictable than stock returns, and does this result vary over time or by industry?\",\"answer\":\"Yes. The analysis finds REITs are more predictable than stocks, and the higher predictability is stable over time and across industries.\"}]","Enhancing real estate investment trust return forecasts using machine learning | PDF",1785675279,83,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"enhancing-real-estate-investment-trust-return-forecasts-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/enhancing-real-estate-investment-trust-return-forecasts-using-machine-learning/117342/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How do machine learning models compare with ordinary least squares for REIT return forecasting?","Question",{"text":75,"@type":76},"Machine learning models provide superior out-of-sample forecasting relative to ordinary least squares models. The study reports improved performance across multiple model families.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What evidence indicates that machine learning forecasts generate economic gains for REIT investors?",{"text":80,"@type":76},"The study links improved predictive performance to significant economic gains when using machine learning forecasts. Better out-of-sample R2 translates into more favorable investor outcomes.",{"name":82,"@type":73,"acceptedAnswer":83},"Are REIT returns more predictable than stock returns, and does this result vary over time or by industry?",{"text":84,"@type":76},"Yes. The analysis finds REITs are more predictable than stocks, and the higher predictability is stable over time and across industries.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]