Pub Date : 2022-08-08DOI: 10.1080/09599916.2022.2105251
Alexander Schiller, René-Ojas Woltering, Christian Weis, Steffen P. Sebastian
ABSTRACT In this paper, we study the mean reversion behaviour of NAV spreads for a global sample of 219 listed real estate stocks. We find NAV spreads for companies trading at a high discount to mean revert fastest. Remarkably, we also provide evidence that online search attention impacts the mean reversion speed of NAV spreads: Stocks with lower levels of online search attention mean-revert significantly faster than those with higher levels. Our global research setting allows us to show that a country’s average NAV spread has an impact on the NAV spreads of individual stocks. Ultimately, we find that the NAV spread of companies receiving high levels of online search attention has a disproportionately high impact on the NAV spreads of other companies.
{"title":"What determines the mean reversion speed of NAV spreads?","authors":"Alexander Schiller, René-Ojas Woltering, Christian Weis, Steffen P. Sebastian","doi":"10.1080/09599916.2022.2105251","DOIUrl":"https://doi.org/10.1080/09599916.2022.2105251","url":null,"abstract":"ABSTRACT In this paper, we study the mean reversion behaviour of NAV spreads for a global sample of 219 listed real estate stocks. We find NAV spreads for companies trading at a high discount to mean revert fastest. Remarkably, we also provide evidence that online search attention impacts the mean reversion speed of NAV spreads: Stocks with lower levels of online search attention mean-revert significantly faster than those with higher levels. Our global research setting allows us to show that a country’s average NAV spread has an impact on the NAV spreads of individual stocks. Ultimately, we find that the NAV spread of companies receiving high levels of online search attention has a disproportionately high impact on the NAV spreads of other companies.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"293 - 320"},"PeriodicalIF":1.9,"publicationDate":"2022-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48827211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1080/09599916.2022.2070525
Anders Hjort, J. Pensar, I. Scheel, D. E. Sommervoll
ABSTRACT Many banks and credit institutions are required to assess the value of dwellings in their mortgage portfolio. This valuation often relies on an Automated Valuation Model (AVM). Moreover, these institutions often report the models accuracy by two numbers: The fraction of predictions within and range from the true values. Until recently, AVMs tended to be hedonic regression models, but lately machine learning approaches like random forest and gradient boosted trees have been increasingly applied. Both the traditional approaches and the machine learning approaches rely on minimising mean squared prediction error, and not the number of predictions in the and range. We investigate whether introducing a loss function closer to the AVMs actual loss measure improves performance in machine learning approaches, specifically for a gradient boosted tree approach. This loss function yields an improvement from to of predictions within of the true value on a data set of transactions from the Norwegian housing market between 2013 and 2015, with the biggest improvements in performance coming from the lower price segments. We also find that a weighted average of models with different loss functions improves performance further, yielding of the observations within of the true value.
{"title":"House price prediction with gradient boosted trees under different loss functions","authors":"Anders Hjort, J. Pensar, I. Scheel, D. E. Sommervoll","doi":"10.1080/09599916.2022.2070525","DOIUrl":"https://doi.org/10.1080/09599916.2022.2070525","url":null,"abstract":"ABSTRACT Many banks and credit institutions are required to assess the value of dwellings in their mortgage portfolio. This valuation often relies on an Automated Valuation Model (AVM). Moreover, these institutions often report the models accuracy by two numbers: The fraction of predictions within and range from the true values. Until recently, AVMs tended to be hedonic regression models, but lately machine learning approaches like random forest and gradient boosted trees have been increasingly applied. Both the traditional approaches and the machine learning approaches rely on minimising mean squared prediction error, and not the number of predictions in the and range. We investigate whether introducing a loss function closer to the AVMs actual loss measure improves performance in machine learning approaches, specifically for a gradient boosted tree approach. This loss function yields an improvement from to of predictions within of the true value on a data set of transactions from the Norwegian housing market between 2013 and 2015, with the biggest improvements in performance coming from the lower price segments. We also find that a weighted average of models with different loss functions improves performance further, yielding of the observations within of the true value.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"338 - 364"},"PeriodicalIF":1.9,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42309261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-03DOI: 10.1080/09599916.2022.2057866
A. Orr, A. Gardner, Cath Jackson, James T. White
ABSTRACT The retailing industry in the UK is experiencing unprecedented structural change. The impact on retailers has often dominated headlines, along with the impacts on local services and economies, but with little attention given to the implications for property owners and practitioners. Exploring and understanding the responsiveness of landlords, and their behaviours, is essential to understanding the adaptiveness of a retailing system. This study employs semi-structured interviews to examine the short- and long-term changes in the retail market and the actions of landlords in response. The findings span the period prior to and during the first year of the Covid-19 pandemic in 2020, and reveal that fundamental changes have occurred to establish tenant covenant norms and the traditional retail leasing model. The paper explores these changes, including a shift in tenant risk, reposition of the leasing model in favour of tenants, generally, and greater application of turnover rents. The pressing challenge for current valuation practitioners, therefore, is to incorporate these fundamental changes within the market into the pricing of retail assets. Significant progress in this area to date, as explored in the paper, has been limited although greater application of discounted cashflow techniques is set to be encouraged by the RICS.
{"title":"Changing tenant covenant perceptions and flexibility in the lease model in UK city centres","authors":"A. Orr, A. Gardner, Cath Jackson, James T. White","doi":"10.1080/09599916.2022.2057866","DOIUrl":"https://doi.org/10.1080/09599916.2022.2057866","url":null,"abstract":"ABSTRACT The retailing industry in the UK is experiencing unprecedented structural change. The impact on retailers has often dominated headlines, along with the impacts on local services and economies, but with little attention given to the implications for property owners and practitioners. Exploring and understanding the responsiveness of landlords, and their behaviours, is essential to understanding the adaptiveness of a retailing system. This study employs semi-structured interviews to examine the short- and long-term changes in the retail market and the actions of landlords in response. The findings span the period prior to and during the first year of the Covid-19 pandemic in 2020, and reveal that fundamental changes have occurred to establish tenant covenant norms and the traditional retail leasing model. The paper explores these changes, including a shift in tenant risk, reposition of the leasing model in favour of tenants, generally, and greater application of turnover rents. The pressing challenge for current valuation practitioners, therefore, is to incorporate these fundamental changes within the market into the pricing of retail assets. Significant progress in this area to date, as explored in the paper, has been limited although greater application of discounted cashflow techniques is set to be encouraged by the RICS.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"40 1","pages":"1 - 24"},"PeriodicalIF":1.9,"publicationDate":"2022-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41999414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1080/09599916.2022.2054353
Elmar Lang, Ferdinand Mager, Kerstin Hennig
ABSTRACT We examine the link between uncertainty and the excess returns of direct commercial real estate markets using the well-established economic policy uncertainty index (EPU) and a novel measure of uncertainty, the world uncertainty index (WUI). Using a panel dataset of 17 European markets, we find a strong positive relation between the two uncertainty measures and excess returns in our univariate models and when we add real estate control variables. However, once macroeconomic control variables are included, only the WUI remains significant. We relate this finding to the more country-specific nature of the WUI, while the EPU potentially gives more weight to global news.
{"title":"Uncertainty and commercial real estate excess returns in European markets","authors":"Elmar Lang, Ferdinand Mager, Kerstin Hennig","doi":"10.1080/09599916.2022.2054353","DOIUrl":"https://doi.org/10.1080/09599916.2022.2054353","url":null,"abstract":"ABSTRACT We examine the link between uncertainty and the excess returns of direct commercial real estate markets using the well-established economic policy uncertainty index (EPU) and a novel measure of uncertainty, the world uncertainty index (WUI). Using a panel dataset of 17 European markets, we find a strong positive relation between the two uncertainty measures and excess returns in our univariate models and when we add real estate control variables. However, once macroeconomic control variables are included, only the WUI remains significant. We relate this finding to the more country-specific nature of the WUI, while the EPU potentially gives more weight to global news.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"321 - 337"},"PeriodicalIF":1.9,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42780407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-14DOI: 10.1080/09599916.2022.2046138
A. Orr, J. Stewart
ABSTRACT This study investigates the relationship between use and investor diversity, spatial accessibility, and high street retail rents. Spatial quantitative analysis of the high street retail sector remains an underdeveloped area so this paper seeks to bridge this gap and contribute to the debate on the adaptability of urban retailing centres by adopting a spatial fixed-effects panel modelling approach. The empirical findings reveal that diversity and richness in property use tend to have a significant positive impact on retail rental values. The influence of ownership richness on rents is positive implying that rents tend to be higher on streets where there is a greater range in the type of landlords. Walkability, as a measure of spatial accessibility, is found to have a negative relationship with market rents. This is perhaps surprising as it had been expected that the most walkable streets in retailing centres to be the most connected and have the highest rents. This contrary finding may be due to large developments interrupting the street network and restricting the choice and movement of pedestrians. Location on the prime retail pitch has a significant positive relationship with shop rents, whereas proximity to transportation nodes has a less consistent influence.
{"title":"Property use diversity and spatial accessibility within urban retailing centres: drivers of retail rents","authors":"A. Orr, J. Stewart","doi":"10.1080/09599916.2022.2046138","DOIUrl":"https://doi.org/10.1080/09599916.2022.2046138","url":null,"abstract":"ABSTRACT This study investigates the relationship between use and investor diversity, spatial accessibility, and high street retail rents. Spatial quantitative analysis of the high street retail sector remains an underdeveloped area so this paper seeks to bridge this gap and contribute to the debate on the adaptability of urban retailing centres by adopting a spatial fixed-effects panel modelling approach. The empirical findings reveal that diversity and richness in property use tend to have a significant positive impact on retail rental values. The influence of ownership richness on rents is positive implying that rents tend to be higher on streets where there is a greater range in the type of landlords. Walkability, as a measure of spatial accessibility, is found to have a negative relationship with market rents. This is perhaps surprising as it had been expected that the most walkable streets in retailing centres to be the most connected and have the highest rents. This contrary finding may be due to large developments interrupting the street network and restricting the choice and movement of pedestrians. Location on the prime retail pitch has a significant positive relationship with shop rents, whereas proximity to transportation nodes has a less consistent influence.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"365 - 392"},"PeriodicalIF":1.9,"publicationDate":"2022-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45619760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-05DOI: 10.1080/09599916.2021.2014937
B. Binoy, M. Naseer, P. P. Anil Kumar
ABSTRACT Land valuation is the process of determining the value of the landed property, excluding all human-made improvements. This paper presents a comprehensive assessment and modelling of the land value and its determinants. Thiruvananthapuram, the capital city of Kerala state, is selected as the study area. Land value modelling applied in this study is divided into three stages. The first stage uses a standard hedonic price model for land value estimation and spatial autocorrelation diagnostics. The spatial error model is appropriate for variable selection and modelling based on Moran’s I and Lagrange Multiplier test statistics in the second stage. The last stage of the study uses the spatial error model for land value analysis, and the results are compared with OLS regression. Proximity to major highways, disaster history, concentration of commercial establishments, and permissible FAR are the major factors affecting land value in the study area. Few other parameters like water frontage and noise pollution have a reverse relationship with similar studies in developed countries. The results indicate that factors influencing land value in Indian cities are different from the European and American cities. The study provides critical insights into the land price variation of an Indian city at a micro-level..
{"title":"Factors affecting land value in an Indian city","authors":"B. Binoy, M. Naseer, P. P. Anil Kumar","doi":"10.1080/09599916.2021.2014937","DOIUrl":"https://doi.org/10.1080/09599916.2021.2014937","url":null,"abstract":"ABSTRACT Land valuation is the process of determining the value of the landed property, excluding all human-made improvements. This paper presents a comprehensive assessment and modelling of the land value and its determinants. Thiruvananthapuram, the capital city of Kerala state, is selected as the study area. Land value modelling applied in this study is divided into three stages. The first stage uses a standard hedonic price model for land value estimation and spatial autocorrelation diagnostics. The spatial error model is appropriate for variable selection and modelling based on Moran’s I and Lagrange Multiplier test statistics in the second stage. The last stage of the study uses the spatial error model for land value analysis, and the results are compared with OLS regression. Proximity to major highways, disaster history, concentration of commercial establishments, and permissible FAR are the major factors affecting land value in the study area. Few other parameters like water frontage and noise pollution have a reverse relationship with similar studies in developed countries. The results indicate that factors influencing land value in Indian cities are different from the European and American cities. The study provides critical insights into the land price variation of an Indian city at a micro-level..","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"268 - 292"},"PeriodicalIF":1.9,"publicationDate":"2022-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43690092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-05DOI: 10.1080/09599916.2021.2023610
M. McCord, D. Lo, J. McCord, P. Davis, M. Haran, P. Turley
ABSTRACT The recent onset of the COVID-19 pandemic has had a pervasive impact on all economies and indeed housing markets. This research investigates the regional impact of the pandemic on the Northern Ireland housing market and provides a unique opportunity to measure short-term reactions to epidemic shocks. Applying a unique dataset, the research measures whether price switching effects are evident as a consequence of the epidemic, and to what extent. In order to achieve this, the research applies spatial lag models to account for the effect of COVID-19 on housing market pricing behaviour. The findings show that the autocorrelation of house prices increased after COVID-19, revealing price persistence driven by behavioural changes. The results further show that a price divergent effect is observable, with the detached sector ‘leading’ the price changes. This price divergence is also apparent for rural dwellings and for neighbourhoods with higher socio-economic standing making them more resistant to the outbreak of COVID-19. This is an important finding as it reveals that epidemics of this nature impact upon housing markets in a heterogeneous way in the short-term, with a clear premium observed for larger housing in healthier and wealthier areas, which may serve to reinforce housing market inequalities.
{"title":"The impact of COVID-19 on house prices in Northern Ireland: price persistence, yet divergent?","authors":"M. McCord, D. Lo, J. McCord, P. Davis, M. Haran, P. Turley","doi":"10.1080/09599916.2021.2023610","DOIUrl":"https://doi.org/10.1080/09599916.2021.2023610","url":null,"abstract":"ABSTRACT The recent onset of the COVID-19 pandemic has had a pervasive impact on all economies and indeed housing markets. This research investigates the regional impact of the pandemic on the Northern Ireland housing market and provides a unique opportunity to measure short-term reactions to epidemic shocks. Applying a unique dataset, the research measures whether price switching effects are evident as a consequence of the epidemic, and to what extent. In order to achieve this, the research applies spatial lag models to account for the effect of COVID-19 on housing market pricing behaviour. The findings show that the autocorrelation of house prices increased after COVID-19, revealing price persistence driven by behavioural changes. The results further show that a price divergent effect is observable, with the detached sector ‘leading’ the price changes. This price divergence is also apparent for rural dwellings and for neighbourhoods with higher socio-economic standing making them more resistant to the outbreak of COVID-19. This is an important finding as it reveals that epidemics of this nature impact upon housing markets in a heterogeneous way in the short-term, with a clear premium observed for larger housing in healthier and wealthier areas, which may serve to reinforce housing market inequalities.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"237 - 267"},"PeriodicalIF":1.9,"publicationDate":"2022-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43647942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-12DOI: 10.1080/09599916.2021.1993314
D. Levy, B. Plester, Raewyn Hills, J. Horan
ABSTRACT Gender diversity in the workplace results in the increased effectiveness of an organisation. However, within the commercial property profession in many countries including New Zealand (as in a number of other professions), only a small number of women are reaching senior positions. This research investigates why this might be. The study comprises one-to-one in-depth interviews with women currently working or who have previously worked in the commercial property profession in Auckland, New Zealand, to develop an understanding of what forces are at play in women’s choices to participate in the commercial property industry in Auckland – or not. Common lived experiences are identified including passion for the industry and the importance of an effective human resources department, they demonstrate gender imbalance, issues around having children, and difficulties around promotions and wage negotiations. Common challenges were workplace bullying, attitudes towards women, socialising, ‘fitting-in’ and coping with male banter. The study concludes that women working in the commercial property profession in New Zealand have thrived through mentorship, taking ownership of their careers and finding a good employer. The insights as to how women perceive the professional commercial property industry can be used to increase effectiveness by increasing gender diversity and inclusion.
{"title":"‘It’s a man’s world’: the lived experiences of women working in the New Zealand professional commercial property industry","authors":"D. Levy, B. Plester, Raewyn Hills, J. Horan","doi":"10.1080/09599916.2021.1993314","DOIUrl":"https://doi.org/10.1080/09599916.2021.1993314","url":null,"abstract":"ABSTRACT Gender diversity in the workplace results in the increased effectiveness of an organisation. However, within the commercial property profession in many countries including New Zealand (as in a number of other professions), only a small number of women are reaching senior positions. This research investigates why this might be. The study comprises one-to-one in-depth interviews with women currently working or who have previously worked in the commercial property profession in Auckland, New Zealand, to develop an understanding of what forces are at play in women’s choices to participate in the commercial property industry in Auckland – or not. Common lived experiences are identified including passion for the industry and the importance of an effective human resources department, they demonstrate gender imbalance, issues around having children, and difficulties around promotions and wage negotiations. Common challenges were workplace bullying, attitudes towards women, socialising, ‘fitting-in’ and coping with male banter. The study concludes that women working in the commercial property profession in New Zealand have thrived through mentorship, taking ownership of their careers and finding a good employer. The insights as to how women perceive the professional commercial property industry can be used to increase effectiveness by increasing gender diversity and inclusion.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"148 - 169"},"PeriodicalIF":1.9,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48595412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-02DOI: 10.1080/09599916.2021.1996447
Carina Kaiser, J. Freybote
ABSTRACT Over the last 20 years, online shopping has evolved into a major threat to the physical retail store. We investigate whether retail real estate investors price e-commerce as an investment risk. In particular, we analyse whether e-commerce sales have informative value for retail real estate returns. Focusing on institutional-grade shopping centres over the period of 2000 to 2018, we find that e-commerce sales predict total returns in the next quarter. This effect is driven by capital returns, which suggests that e-commerce is indeed priced as an investment risk. While consistent across mall types, this effect is stronger for regional and super-regional malls than neighbourhood and community shopping centres. Explanations for this difference include the types of retail tenants in these different mall categories and the varying impact of e-commerce on their business.
{"title":"Is e-commerce an investment risk priced by retail real estate investors? An investigation","authors":"Carina Kaiser, J. Freybote","doi":"10.1080/09599916.2021.1996447","DOIUrl":"https://doi.org/10.1080/09599916.2021.1996447","url":null,"abstract":"ABSTRACT Over the last 20 years, online shopping has evolved into a major threat to the physical retail store. We investigate whether retail real estate investors price e-commerce as an investment risk. In particular, we analyse whether e-commerce sales have informative value for retail real estate returns. Focusing on institutional-grade shopping centres over the period of 2000 to 2018, we find that e-commerce sales predict total returns in the next quarter. This effect is driven by capital returns, which suggests that e-commerce is indeed priced as an investment risk. While consistent across mall types, this effect is stronger for regional and super-regional malls than neighbourhood and community shopping centres. Explanations for this difference include the types of retail tenants in these different mall categories and the varying impact of e-commerce on their business.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"197 - 214"},"PeriodicalIF":1.9,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45683393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1080/09599916.2021.1996446
Xiaojie Xu, Yun Zhang
ABSTRACT The house market in China has been growing rapidly for the past decade and price forecasting has become a significant issue to the people and policymakers. We approach this problem by examining neural networks for second-hand house price index forecasting from 10 major cities for March 2012–May 2020. Our purpose is to build simple and accurate neural networks to contribute to pure technical house price forecasting of the Chinese market. We explore various model settings across the algorithm, delay, hidden neuron, and data spitting ratio, and arrive at a rather simple neural network with three delays and eight hidden neurons, which leads to stable performance of 0.8% average relative root-mean-square error across the 10 cities for the training, validation, and testing phases. Results here can be used on a standalone basis or combined with fundamental forecasting in forming perspectives of house price trends and conducting policy analysis.
{"title":"Second-hand house price index forecasting with neural networks","authors":"Xiaojie Xu, Yun Zhang","doi":"10.1080/09599916.2021.1996446","DOIUrl":"https://doi.org/10.1080/09599916.2021.1996446","url":null,"abstract":"ABSTRACT The house market in China has been growing rapidly for the past decade and price forecasting has become a significant issue to the people and policymakers. We approach this problem by examining neural networks for second-hand house price index forecasting from 10 major cities for March 2012–May 2020. Our purpose is to build simple and accurate neural networks to contribute to pure technical house price forecasting of the Chinese market. We explore various model settings across the algorithm, delay, hidden neuron, and data spitting ratio, and arrive at a rather simple neural network with three delays and eight hidden neurons, which leads to stable performance of 0.8% average relative root-mean-square error across the 10 cities for the training, validation, and testing phases. Results here can be used on a standalone basis or combined with fundamental forecasting in forming perspectives of house price trends and conducting policy analysis.","PeriodicalId":45726,"journal":{"name":"Journal of Property Research","volume":"39 1","pages":"215 - 236"},"PeriodicalIF":1.9,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46823697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：