The nonlinearity of hedonic datasets demands flexible automated valuation models to appraise housing prices accurately,and artificial intelligence models have been employed in mass appraisal to this end.However,they h...The nonlinearity of hedonic datasets demands flexible automated valuation models to appraise housing prices accurately,and artificial intelligence models have been employed in mass appraisal to this end.However,they have been referred to as“blackbox”models owing to difficulties associated with interpretation.In this study,we compared the results of traditional hedonic pricing models with those of machine learning algorithms,e.g.,random forest and deep neural network models.Commonly implemented measures,e.g.,Gini importance and permutation importance,provide only the magnitude of each explanatory variable’s importance,which results in ambiguous interpretability.To address this issue,we employed the SHapley Additive exPlanation(SHAP)method and explored its effectiveness through comparisons with traditionally explainable measures in hedonic pricing models.The results demonstrated that(1)the random forest model with the SHAP method could be a reliable instrument for appraising housing prices with high accuracy and sufficient interpretability,(2)the interpretable results retrieved from the SHAP method can be consolidated by the support of statistical evidence,and(3)housing characteristics and local amenities are primary contributors in property valuation,which is consistent with the findings of previous studies.Thus,our novel methodological framework and robust findings provide informative insights into the use of machine learning methods in property valuation based on the comparative analysis.展开更多
This study examines the impact of futures trading on market efficiency and price discovery in the U.S.real estate investment trusts(REITs)market.First,we present inconclusive evidence regarding efficiency improvement ...This study examines the impact of futures trading on market efficiency and price discovery in the U.S.real estate investment trusts(REITs)market.First,we present inconclusive evidence regarding efficiency improvement in the U.S.REIT spot market following the introduction of futures trading.To investigate the interplay between spot and futures markets,we analyze their respective roles in price discovery and find that,unlike in stock and bond markets,the spot market predominantly exhibits price leadership in the U.S.REITs market,despite the growing market size of futures.We find evidence that the limited role of futures in price discovery is associated with an increase in speculative demand,which outweighs hedging pressure.These findings suggest that policymakers should carefully monitor investor trading motives in the U.S.REITs market and consider revising market regulations to enhance liquidity,ensuring that increased liquidity does not primarily result from heightened speculative demand.展开更多
This study explains the role of economic uncertainty as a bridge between business cycles and investors’herding behavior.Starting with a conventional stochastic differential equation representing the evolution of stoc...This study explains the role of economic uncertainty as a bridge between business cycles and investors’herding behavior.Starting with a conventional stochastic differential equation representing the evolution of stock returns,we provide a simple theoretical model and empirically demonstrate it.Specifically,the growth rate of gross domestic product and the power law exponent are used as proxies for business cycles and herding behavior,respectively.We find stronger herding behavior during recessions than during booms.We attribute this to economic uncertainty,which leads to strong behavioral bias in the stock market.These findings are consistent with the predictions of the quantum model.展开更多
基金supported by the National Research Foundation of Korea grant funded by the Korea government(MSIT)(RS-2025-16067531:Kwangwon Ahn)Hankuk University of Foreign Studies Research Fund(0f 2025:Sihyun An).
文摘The nonlinearity of hedonic datasets demands flexible automated valuation models to appraise housing prices accurately,and artificial intelligence models have been employed in mass appraisal to this end.However,they have been referred to as“blackbox”models owing to difficulties associated with interpretation.In this study,we compared the results of traditional hedonic pricing models with those of machine learning algorithms,e.g.,random forest and deep neural network models.Commonly implemented measures,e.g.,Gini importance and permutation importance,provide only the magnitude of each explanatory variable’s importance,which results in ambiguous interpretability.To address this issue,we employed the SHapley Additive exPlanation(SHAP)method and explored its effectiveness through comparisons with traditionally explainable measures in hedonic pricing models.The results demonstrated that(1)the random forest model with the SHAP method could be a reliable instrument for appraising housing prices with high accuracy and sufficient interpretability,(2)the interpretable results retrieved from the SHAP method can be consolidated by the support of statistical evidence,and(3)housing characteristics and local amenities are primary contributors in property valuation,which is consistent with the findings of previous studies.Thus,our novel methodological framework and robust findings provide informative insights into the use of machine learning methods in property valuation based on the comparative analysis.
基金supported by the National Research Foundation of Korea funded by the Ministry of Science and ICT(2022R1A2C1004258:Kwangwon Ahn)the Sogang University Research Grant of 2023(No.202310016.01:Sungbin Sohn).
文摘This study examines the impact of futures trading on market efficiency and price discovery in the U.S.real estate investment trusts(REITs)market.First,we present inconclusive evidence regarding efficiency improvement in the U.S.REIT spot market following the introduction of futures trading.To investigate the interplay between spot and futures markets,we analyze their respective roles in price discovery and find that,unlike in stock and bond markets,the spot market predominantly exhibits price leadership in the U.S.REITs market,despite the growing market size of futures.We find evidence that the limited role of futures in price discovery is associated with an increase in speculative demand,which outweighs hedging pressure.These findings suggest that policymakers should carefully monitor investor trading motives in the U.S.REITs market and consider revising market regulations to enhance liquidity,ensuring that increased liquidity does not primarily result from heightened speculative demand.
基金supported by the National Research Foundation of Korea grant funded by the Korean government(No.2022R1A2C100425811,Kwangwon Ahn).
文摘This study explains the role of economic uncertainty as a bridge between business cycles and investors’herding behavior.Starting with a conventional stochastic differential equation representing the evolution of stock returns,we provide a simple theoretical model and empirically demonstrate it.Specifically,the growth rate of gross domestic product and the power law exponent are used as proxies for business cycles and herding behavior,respectively.We find stronger herding behavior during recessions than during booms.We attribute this to economic uncertainty,which leads to strong behavioral bias in the stock market.These findings are consistent with the predictions of the quantum model.
