scholarly journals Sentiment-based predictions of housing market turning points with Google trends

2016 ◽  
Vol 9 (1) ◽  
pp. 108-136 ◽  
Author(s):  
Marian Alexander Dietzel
Keyword(s):  
Real Estate ◽  
Housing Market ◽  
Turning Points ◽  
House Price ◽  
Data Set ◽  
Content Type ◽  
Forecasting Models ◽  
Search Volume ◽  
Out Of Sample ◽  
Google Search

Purpose – Recent research has found significant relationships between internet search volume and real estate markets. This paper aims to examine whether Google search volume data can serve as a leading sentiment indicator and are able to predict turning points in the US housing market. One of the main objectives is to find a model based on internet search interest that generates reliable real-time forecasts. Design/methodology/approach – Starting from seven individual real-estate-related Google search volume indices, a multivariate probit model is derived by following a selection procedure. The best model is then tested for its in- and out-of-sample forecasting ability. Findings – The results show that the model predicts the direction of monthly price changes correctly, with over 89 per cent in-sample and just above 88 per cent in one to four-month out-of-sample forecasts. The out-of-sample tests demonstrate that although the Google model is not always accurate in terms of timing, the signals are always correct when it comes to foreseeing an upcoming turning point. Thus, as signals are generated up to six months early, it functions as a satisfactory and timely indicator of future house price changes. Practical implications – The results suggest that Google data can serve as an early market indicator and that the application of this data set in binary forecasting models can produce useful predictions of changes in upward and downward movements of US house prices, as measured by the Case–Shiller 20-City House Price Index. This implies that real estate forecasters, economists and policymakers should consider incorporating this free and very current data set into their market forecasts or when performing plausibility checks for future investment decisions. Originality/value – This is the first paper to apply Google search query data as a sentiment indicator in binary forecasting models to predict turning points in the housing market.

scholarly journals International Real Estate Review

2020 ◽  
Vol 23 (2) ◽  
pp. 267-308
Author(s):  
Are Oust ◽  
◽  
Ole Martin Eidjord ◽  
Keyword(s):  
Real Estate ◽  
Housing Market ◽  
House Prices ◽  
House Price ◽  
Search Term ◽  
Housing Bubble ◽  
Search Terms ◽  
Search Volume ◽  
Google Search ◽  
The U.S

The aim of this paper is to test whether Google search volume indices can be used to predict house prices and identify bubbles in the housing market. We analyze the data that pertain to the 2006?2007 U.S. housing bubble, taking advantage of the heterogeneous house price development in both bubble and non-bubble states in the U.S. Using 204 housing-related keywords, we test both single search terms and indices that comprise search term sets to see whether they can be used as housing bubble indicators. We find that several keywords perform very well as bubble indicators. Among all of the keywords and indices tested, the Google search volume for ¡§Housing Bubble¡¨ and ¡§Real Estate Agent¡¨, and a constructed index that contains the twelve best-performing search terms score the highest at both detecting bubbles and not erroneously detecting non-bubble states as bubbles. A new housing bubble indicator may help households, investors, and policy makers receive advanced warning about future housing bubbles. Moreover, we show that the Google search outperforms the well-established consumer confidence index in the U.S. as a leading indicator of the housing market.

House price index (HPI) and Covid-19 pandemic shocks: evidence from Turkey and Kazakhstan

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yeşim Aliefendioğlu ◽  
Harun Tanrivermis ◽  
Monsurat Ayojimi Salami
Keyword(s):  
Real Estate ◽  
Price Index ◽  
Housing Prices ◽  
House Price ◽  
Monthly Basis ◽  
Data Set ◽  
House Price Index ◽  
Content Type ◽  
Asymmetric Pricing ◽  
Long Run

Purpose This paper aims to investigate asymmetric pricing behaviour and impact of coronavirus (Covid-19) pandemic shocks on house price index (HPI) of Turkey and Kazakhstan. Design/methodology/approach Monthly HPIs and consumer price index (CPI) data ranges from 2010M1 to 2020M5 are used. This study uses a nonlinear autoregressive distributed lag model for empirical analysis. Findings The findings of this study reveal that the Covid-19 pandemic exerted both long-run and short-run asymmetric relationship on HPI of Turkey while in Kazakhstan, the long-run impact of Covid-19 pandemic shock is symmetrical long-run positive effect is similar in both HPI markets. Research limitations/implications The main limitations of this study are the study scope and data set due to data constraint. Several other macroeconomic variables may affect housing prices; however, variables used in this study satisfy the focus of this study in the presence of data constraint. HPI and CPI variables were made available on monthly basis for a considerably longer period which guaranteed the ranges of data set used in this study. Practical implications Despite the limitation, this study provides necessary information for authorities and prospective investors in HPI to make a sound investment decision. Originality/value This is the first study that rigorously and simultaneously examines the pricing behaviour of Turkey and Kazakhstan HPIs in relation to the Covid-19 pandemic shocks at the regional level. HPI of Kazakhstan is recognized in the global real estate transparency index but the study is rare. The study contributes to regional studies on housing price by bridging this gap in the real estate literature.

Spatial effects and non-linearity in hedonic modeling

2018 ◽  
Vol 36 (1) ◽  
pp. 32-49 ◽  
Author(s):  
Marcelo Cajias ◽  
Sebastian Ertl
Keyword(s):  
Real Estate ◽  
Functional Form ◽  
Asymptotic Properties ◽  
Additive Model ◽  
Percentage Error ◽  
Spatial Effects ◽  
Hedonic Models ◽  
Data Set ◽  
Content Type ◽  
Out Of Sample

Purpose The purpose of this paper is to test the asymptotic properties and prediction accuracy of two innovative methods proposed along the hedonic debate: the geographically weighted regression (GWR) and the generalized additive model (GAM). Design/methodology/approach The authors assess the asymptotic properties of linear, spatial and non-linear hedonic models based on a very large data set in Germany. The employed functional form is based on the OLS, GWR and the GAM, while the estimation methodology was chosen to be iterative in forecasting, the fitted rents for each quarter based on their 1-quarter-prior functional form. The performance accuracy is measured by traditional indicators such as the error variance and the mean squared (percentage) error. Findings The results provide evidence for a clear disadvantage of the GWR model in out-of-sample forecasts. There exists a strong out-of-sample discrepancy between the GWR and the GAM models, whereas the simplicity of the OLS approach is not substantially outperformed by the GAM approach. Practical implications For policymakers, a more accurate knowledge on market dynamics via hedonic models leads to a more precise market control and to a better understanding of the local factors affecting current and future rents. For institutional researchers, instead, the findings are essential and might be used as a guide when valuing residential portfolios and forecasting cashflows. Even though this study analyses residential real estate, the results should be of interest to all forms of real estate investments. Originality/value Sample size is essential when deriving the asymptotic properties of hedonic models. Whit this study covering more than 570,000 observations, this study constitutes – to the authors’ knowledge – one of the largest data sets used for spatial real estate analysis.

scholarly journals Outperforming the benchmark: online information demand and REIT market performance

2015 ◽  
Vol 33 (2) ◽  
pp. 169-195 ◽  
Author(s):  
Karim Rochdi ◽  
Marian Dietzel
Keyword(s):  
Real Estate ◽  
Online Information ◽  
Investment Strategies ◽  
Content Type ◽  
Search Volume ◽  
Information Demand ◽  
The Us ◽  
Google Search ◽  
Practical Implications ◽  
Successful Predictor

Purpose – The purpose of this paper is to investigate whether there is a relationship between asset-specific online search interest and movements in the US REIT market. Design/methodology/approach – The authors collect search volume (SV) data from “Google Trends” for a set of keywords representing the information demand of real estate (equity) investors. On this basis, the authors test hypothetical investment strategies based on changes in internet SV, to anticipate REIT market movements. Findings – The results reveal that people’s information demand can indeed serve as a successful predictor for the US REIT market. Among other findings, evidence is provided that there is a significant relationship between asset-specific keywords and the US REIT market. Specifically, investment strategies based on weekly changes in Google SV would have outperformed a buy-and-hold strategy (0.1 percent p.a.) for the Morgan Stanley Capital International US REIT Index by a remarkable 15.4 percent p.a. between 2006 and 2013. Furthermore, the authors find that real-estate-related terms are more suitable than rather general, finance-related terms for predicting REIT market movements. Practical implications – The findings should be of particular interest for REIT market investors, as the established relationships can potentially be utilized to anticipate short-term REIT market movements. Originality/value – This is the first paper which applies Google search query data to the REIT market.

Estimating the housing price with a search-and-matching model

2015 ◽  
Vol 8 (2) ◽  
pp. 196-216
Author(s):  
Gaetano Lisi ◽  
Mauro Iacobini
Keyword(s):  
Theoretical Model ◽  
Real Estate ◽  
Housing Market ◽  
House Price ◽  
Price Adjustment ◽  
Selling Price ◽  
Search And Matching ◽  
Content Type ◽  
Time On The Market ◽  
Matching Models

Purpose – This paper aims to pose an important starting point for the application of the search-and-matching models to real estate appraisals, thus reducing the “gap” between practitioners and academicians. Due to relevant trading frictions, the search-and-matching framework has become the benchmark theoretical model of the housing market. Starting from the large related literature, this paper develops a simplified approach to modelling the frictions that focuses on the direct relationship between house price and market tightness (a common feature only for the labour market matching models). The characterization of the equilibrium through two main variables simplifies the analysis and allows using the theoretical model for empirical purposes, namely, the real estate appraisals. Design/methodology/approach – This work is both theoretical and empirical. Theoretically, a long-run equilibrium model with a positive share of vacant houses and home seekers is determined along with price and market tightness. Also, the conditions of existence and uniqueness of the steady-state equilibrium are determined. Unlike most of the search-and-matching models in the housing literature, the out-of-the steady-state dynamics are also analyzed to show the stability of the equilibrium. Empirically, to show the usefulness of the theoretical model, a numerical simulation is performed. By using two readily available housing market data – the expected time on the market and the average number of trades – it is possible to determine the key variables of the model: price, market tightness and matching opportunities for both buyers and sellers. Although the numerical simulation concerns the Italian housing market, the proposed model is generally valid, being empirically applicable to all real estate markets characterized by non-negligible trading frictions. Indeed, the proposed model can be used to compare housing markets with different features (concerning the search and matching process), as well as analyse the same housing market in different time periods (because the efficiency of the search and matching process can change). Findings – Several important results are obtained. First, the price adjustment – i.e. the difference between the actual selling price and the price obtained in an ideal situation of frictionless housing market – is remarkable. This means that the sign and the size of the price adjustment depend on the extent of trading frictions in the housing market. Precisely, the higher the trading frictions on the demand side (more buyers and less sellers), the higher the actual selling price (the price adjustment is positive), whereas the higher the trading frictions on the supply side (less buyers and more sellers), the lower the actual selling price (the price adjustment is negative). Accordingly, the real estate appraisers should assess the trading frictions in the housing market before determining the price adjustment. Second, an increase in the number of trades affects the house price only if the time on the market varies. Also, the higher the variation in the time on the market, the larger the house price adjustment. Indeed, the expected time on the market reflects the opportunities to matching for both parties and thus the trading frictions. If the time on the market increases (decreases), the seller will receive less (more) opportunities to match; thus, the actual selling price will be driven downwards (upwards). Originality/value – As far as the authors are aware, none of the existing works in the search and matching literature has considered how to take advantage of this theoretical approach to estimate the house price in the presence of trading frictions in the housing market. Indeed, the proposed theoretical model may be a useful tool for real estate appraisers, as it is able to derive the trading frictions from the time on the market and the number of trades, thus estimating properly the house price.

scholarly journals Forecasting the Finnish house price returns and volatility: a comparison of time series models

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Josephine Dufitinema
Keyword(s):  
Moving Average ◽  
House Price ◽  
Arma Model ◽  
Price Volatility ◽  
Data Set ◽  
Content Type ◽  
Out Of Sample ◽  
Egarch Model ◽  
House Price Volatility ◽  
Arfima Model

Purpose The purpose of this paper is to compare different models’ performance in modelling and forecasting the Finnish house price returns and volatility. Design/methodology/approach The competing models are the autoregressive moving average (ARMA) model and autoregressive fractional integrated moving average (ARFIMA) model for house price returns. For house price volatility, the exponential generalized autoregressive conditional heteroscedasticity (EGARCH) model is competing with the fractional integrated GARCH (FIGARCH) and component GARCH (CGARCH) models. Findings Results reveal that, for modelling Finnish house price returns, the data set under study drives the performance of ARMA or ARFIMA model. The EGARCH model stands as the leading model for Finnish house price volatility modelling. The long memory models (ARFIMA, CGARCH and FIGARCH) provide superior out-of-sample forecasts for house price returns and volatility; they outperform their short memory counterparts in most regions. Additionally, the models’ in-sample fit performances vary from region to region, while in some areas, the models manifest a geographical pattern in their out-of-sample forecasting performances. Research limitations/implications The research results have vital implications, namely, portfolio allocation, investment risk assessment and decision-making. Originality/value To the best of the author’s knowledge, for Finland, there has yet to be empirical forecasting of either house price returns or/and volatility. Therefore, this study aims to bridge that gap by comparing different models’ performance in modelling, as well as forecasting the house price returns and volatility of the studied market.

scholarly journals Land price dynamics in a large Australian urban housing market

2014 ◽  
Vol 7 (1) ◽  
pp. 42-60 ◽  
Author(s):  
Greg Costello
Keyword(s):  
Housing Market ◽  
Price Change ◽  
House Price ◽  
Housing Markets ◽  
Urban Housing ◽  
Price Dynamics ◽  
Data Set ◽  
Content Type ◽  
Hedonic Price Analysis ◽  
Spatial Disaggregation

Purpose – Housing is a composite asset comprising land and improved components varying as proportions of total value over space and time. Theory suggests land and improvements (structures) are unique goods responding differently to economic stimuli. This paper aims to test the expectation of different overall house price changes in response to variation in land and improved components. Design/methodology/approach – House price dynamics are decomposed to analyse the influence of land and structure components for the city of Perth, Australia both at aggregate level and for spatially defined housing sub-regions, sample period 1995-2010. Findings – Values of land and improvements on that land evolve differently over time and are significantly influenced by the magnitude of land leverage. The study extends previous research through extensive spatial disaggregation of a larger more detailed data set than previously used in studies of this type confirming significant variation in land leverage ratios, overall price change and growth rates for land and improvements in sub-regional markets defined by spatial criteria. Research limitations/implications – The results suggest an important role for policy development with respect to housing affordability and supply side regulation of land in large urban housing markets. Practical implications – The results suggest important implications for hedonic price analysis of housing markets. The inclusion of land leverage variables in hedonic regression could remove coefficient bias associated with omitted location amenity variables. Originality/value – The paper adapts methodology from previous studies but extends previous literature through detailed analysis of a large Australian housing market (Perth) enabling extensive spatial disaggregation of the sample and providing greater insight to spatial variation of land leverage than in previous studies.

Sentiment-based commercial real estate forecasting with Google search volume data

2014 ◽  
Vol 32 (6) ◽  
pp. 540-569 ◽  
Author(s):  
Marian Alexander Dietzel ◽  
Nicole Braun ◽  
Wolfgang Schäfers
Keyword(s):  
Real Estate ◽  
Commercial Real Estate ◽  
Google Trends ◽  
Internet Search ◽  
Price Indices ◽  
Search Query ◽  
Content Type ◽  
Forecasting Models ◽  
Search Data ◽  
Google Search

Purpose – The purpose of this paper is to examine internet search query data provided by “Google Trends”, with respect to its ability to serve as a sentiment indicator and improve commercial real estate forecasting models for transactions and price indices. Design/methodology/approach – This paper examines internet search query data provided by “Google Trends”, with respect to its ability to serve as a sentiment indicator and improve commercial real estate forecasting models for transactions and price indices. Findings – The empirical results show that all models augmented with Google data, combining both macro and search data, significantly outperform baseline models which abandon internet search data. Models based on Google data alone, outperform the baseline models in all cases. The models achieve a reduction over the baseline models of the mean squared forecasting error for transactions and prices of up to 35 and 54 per cent, respectively. Practical implications – The results suggest that Google data can serve as an early market indicator. The findings of this study suggest that the inclusion of Google search data in forecasting models can improve forecast accuracy significantly. This implies that commercial real estate forecasters should consider incorporating this free and timely data set into their market forecasts or when performing plausibility checks for future investment decisions. Originality/value – This is the first paper applying Google search query data to the commercial real estate sector.

A multifractal detrended fluctuation analysis of housing market: a role of financial crises in developed economies

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Syed Ali Raza ◽  
Nida Shah ◽  
Muhammad Tahir Suleman ◽  
Md Al Mamun
Keyword(s):  
Financial Crisis ◽  
Housing Market ◽  
Market Efficiency ◽  
House Price ◽  
Fluctuation Analysis ◽  
Content Type ◽  
Multifractal Detrended Fluctuation Analysis ◽  
Long Run ◽  
Before And After

Purpose This study aims to examine the house price fluctuations in G7 countries by using the multifractal detrended fluctuation analysis (MF-DFA) for the years 1970–2019. The study examined the market efficiency between the short-term and long-term in the full sample period, before and after the global financial crisis period. Design/methodology/approach This study uses the MF-DFA to analyze house price fluctuations. Findings The findings confirmed that the housing market series are multifractal. Furthermore, all the markets showed long-term persistence in both the short and long-term. The USA is identified as the most persistent house market in the short run and Japan in the long run. Moreover, in terms of efficiency, Canada is identified as the most efficient house market in the long run and the UK in the short run. Finally, the result of before and after the financial crisis period is consistent with the full sample result. Originality/value The contribution of this study in the literature is fourfold. This is the first study that has examined the house prices efficiency by using the MF-DFA technique given by Kantelhardt et al. (2002). Previously, the house market prices and efficiency has been investigated using generalized Hurst exponent (Liu et al., 2019), Quantile Regression Approach (Chae and Bera, 2019; Tiwari et al., 2019) but no study to the best of the knowledge has been done that has used the MF-DFA technique on the housing market. Second, this is the first study that has focused on the house markets of G7 countries. Third, this study explores the house market efficiency by dividing the market into two periods i.e. before and after the financial crisis. The study strives to investigate if the financial crisis determines the change in the degree of market efficiency or not. Finally, the study gives valuable insights to the investors that will help them in their investment decisions.

Information search in times of market uncertainty: an examination of aggregate and disaggregate uncertainty

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Marshall A. Geiger ◽  
Rajib Hasan ◽  
Abdullah Kumas ◽  
Joyce van der Laan Smith
Keyword(s):  
Information Search ◽  
Institutional Investors ◽  
Volume Index ◽  
Individual Investor ◽  
Market Uncertainty ◽  
Data Set ◽  
Current Time ◽  
Content Type ◽  
Information Demand ◽  
Google Search

PurposeThis study explores the association between individual investor information demand and two measures of market uncertainty – aggregate market uncertainty and disaggregate industry-specific market uncertainty. It extends the literature by being the first to empirically examine investor information demand and disaggregate market uncertainty.Design/methodology/approachThis paper constructs a measure of information search by using the Google Search Volume Index and computes measures of aggregate and disaggregate market uncertainty using institutional investors' trading data from Ancerno Ltd. The relation between market uncertainty, as measured by trading disagreements among institutional investors, and information search is analyzed using an OLS (Ordinary Least Squares) regression model.FindingsThis paper finds that individual investor information demand is significantly and positively correlated with aggregate market uncertainty but not associated with disaggregated industry uncertainty. The findings suggest that individual investors may not fully incorporate all relevant uncertainty information and that ambiguity-related market pricing anomalies may be more associated with disaggregate market uncertainty.Research limitations/implicationsThis study presents an examination of aggregate and disaggregate measures of market uncertainty and individual investor demand for information, shedding light on the efficiency of the market in incorporating information. A limitation of our study is that our data for market uncertainty is based on investor trading disagreement from Ancerno, Ltd. which is only available till 2011. However, we believe the implications are generalizable to the current time period.Practical implicationsThis study provides the first concurrent empirical assessment of investor information search and aggregate and disaggregate market uncertainty. Prior research has separately examined information demand in these two types of market uncertainty. Thus, this study provides information to investors regarding the importance of assessing disaggregate component measures of the market.Originality/valueThis paper is the first to empirically examine investor information search and disaggregate market uncertainty. It also employs a unique data set and method to determine disaggregate, and aggregate, market uncertainty.

Sign in / Sign up

Export Citation Format

Share Document