The role of investor sentiment in forecasting housing returns in China: A machine learning approach

作     者：Cepni, Oguzhan Gupta, Rangan Onay, Yigit 

作者机构：Copenhagen Business Sch DK-2000 Frederiksberg Denmark Cent Bank Republ Turkey Ankara Turkey Univ Pretoria Dept Econ Pretoria South Africa 

出 版 物：《JOURNAL OF FORECASTING》 (J Forecast)

年 卷 期：2022年第41卷第8期

页      面：1725-1740页

核心收录：

学科分类：0201[经济学-理论经济学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 08[工学] 

基　　金：We would like to thank anonymous referees for many helpful comments. However  any remaining errors are solely ours 

主　　题：Bayesian shrinkage housing prices investor sentiment time-varying parameter model 

摘      要：This paper analyzes the predictive ability of aggregate and disaggregate proxies of investor sentiment, over and above standard macroeconomic predictors, in forecasting housing returns in China, using an array of machine learning models. We find that our new aligned investor sentiment index has greater predictive power for housing returns than the principal component analysis (PCA)-based sentiment index, used earlier in the literature. Moreover, shrinkage models utilizing the disaggregate sentiment proxies do not result in forecast improvement indicating that aligned sentiment index optimally exploits information in the disaggregate proxies of investor sentiment. Furthermore, when we let the machine learning models to choose from all key control variables and the aligned sentiment index, the forecasting accuracy is improved at all forecasting horizons, rather than just the short-run as witnessed under standard predictive regressions. This result suggests that machine learning methods are flexible enough to capture both structural change and time-varying information in a set of predictors simultaneously to forecast housing returns of China in a precise manner. Given the role of the real estate market in China s economic growth, our result of accurate forecasting of housing returns has important implications for both investors and policymakers.