Artificial intelligence, news sentiment, and property market liquidity

2019 ◽  
Vol 38 (4) ◽  
pp. 309-325
Author(s):  
Johannes Braun ◽  
Jochen Hausler ◽  
Wolfgang Schäfers
Keyword(s):  
Artificial Intelligence ◽  
Real Estate ◽  
Real Estate Market ◽  
Global Market ◽  
Price Impact ◽  
Market Liquidity ◽  
Property Market ◽  
Content Type ◽  
Market Sentiment ◽  
Distributed Lag

Purpose The purpose of this paper is to use a text-based sentiment indicator to explain variations in direct property market liquidity in the USA. Design/methodology/approach By means of an artificial neural network, market sentiment is extracted from 66,070 US real estate market news articles from the S&P Global Market Intelligence database. For training of the network, a distant supervision approach utilizing 17,822 labeled investment ideas from the crowd-sourced investment advisory platform Seeking Alpha is applied. Findings According to the results of autoregressive distributed lag models including contemporary and lagged sentiment as independent variables, the derived textual sentiment indicator is not only significantly linked to the depth and resilience dimensions of market liquidity (proxied by Amihud’s (2002) price impact measure), but also to the breadth dimension (proxied by transaction volume). Practical implications These results suggest an intertemporal effect of sentiment on liquidity for the direct property market. Market participants should account for this effect in terms of their investment decisions, and also when assessing and pricing liquidity risk. Originality/value This paper not only extends the literature on text-based sentiment indicators in real estate, but is also the first to apply artificial intelligence for sentiment extraction from news articles in a market liquidity setting.

Cyclical capitalization and lag vacancy

2017 ◽  
Vol 10 (2) ◽  
pp. 211-238 ◽  
Author(s):  
Maurizio d’Amato
Keyword(s):  
Real Estate ◽  
Market Value ◽  
Real Estate Market ◽  
Mortgage Lending ◽  
Property Market ◽  
Content Type ◽  
The Real ◽  
The Real Estate ◽  
The Real Estate Market ◽  
Valuation Process

Purpose This paper aims to propose a new valuation method for income producing properties. The model originally called cyclical dividend discount models (d’Amato, 2003) has been recently proposed as a family of income approach methodologies called cyclical capitalization (d’Amato, 2013; d’Amato, 2015; d’Amato, 2017). Design/methodology/approach The proposed methodology tries to integrate real estate market cycle analysis and forecast inside the valuation process allowing the appraiser to deal with real estate market phases analysis and their consequence in the local real estate market. Findings The findings consist in the creation of a methodology proposed for market value and in particular for mortgage lending determination, as the model may have the capability to reach prudent opinion of value in all the real estate market phase. Research limitations/implications Research limitation consists mainly in a limited number of sample of time series of rent and in the forecast of more than a cap rate or yield rate even if it is quite commonly accepted the cyclical nature of the real estate market. Practical implications The implication of the proposed methodology is a modified approach to direct capitalization finding more flexible approaches to appraise income producing properties sensitive to the upturn and downturn of the real estate market. Social implications The model proposed can be considered useful for the valuation process of those property affected by the property market cycle, both in the mortgage lending and market value determination. Originality/value These methodologies try to integrate in the appraisal process the role of property market cycles. Cyclical capitalization modelling includes in the traditional dividend discount model more than one g-factor to plot property market cycle dealing with the future in a different way. It must be stressed the countercyclical nature of the cyclical capitalization that may be helpful in the determination of mortgage lending value. This is a very important characteristic of such models.

Cycology – what has been learnt from previous real estate cycles?

2017 ◽  
Vol 35 (4) ◽  
pp. 427-435
Author(s):  
Simon Durkin
Keyword(s):  
Real Estate ◽  
Property Market ◽  
Content Type ◽  
Market Sentiment ◽  
Lessons Learnt ◽  
Quantitative Property ◽  
The Future ◽  
Future Challenges ◽  
Current Cycle ◽  
Industry Professionals

Purpose The purpose of this paper is to look at the lessons learnt from the previous real estate cycles based on a sample of investors, occupiers and academics and seek to understand the practical challenges the industry faces in the current cycle. Design/methodology/approach The paper summarises the results of qualitative research and interviews conducted and analysed by BNP Paribas Real Estate and Ipsos MORI. Findings The paper considers the crisis of 2008, its impact on performance, lessons learnt by the industry as a result and the future challenges. Whilst the industry felt well prepared to withstand future uncertainty and change, there was concern that subsequent generations of industry professionals will not be well equipped to deal with the pace and magnitude of change. Practical implications This is a practical study that seeks to place a greater emphasis on the drivers of market sentiment rather than focussing on quantitative forecasts. Originality/value There is much attention given to quantitative property market forecasts; however, there seems to be little appreciation of the need to evolve our process in today’s fast paced, structurally changing market which will behave differently to how it has in the past. Economic forecasts have received much criticism recently and these provide the basis for property market forecasts. The consideration of sentiment and the qualitative aspect of the future drivers of performance have never been so critical.

scholarly journals Long lease real estate – a revised role for real estate in pension fund portfolios

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Nick Mansley ◽  
Zilong Wang
Keyword(s):  
Real Estate ◽  
Pension Fund ◽  
Real Estate Market ◽  
Property Market ◽  
Short Term ◽  
Content Type ◽  
Fund Managers ◽  
Regulatory Guidance ◽  
And Performance ◽  
Dramatic Growth

PurposeLong lease real estate funds (over £15bn in Q3 2020) have emerged as an increasingly important part of UK pension fund real estate portfolios. This paper explores the reasons for their dramatic growth, their characteristics and performance.Design/methodology/approachThis study uses data for the period 2004–2020 collected directly from fund managers and from AREF/MSCI and empirical analysis to explore their characteristics and performance.FindingsPension fund de-risking and regulatory guidance have supported the dramatic growth of long lease real estate funds. Long lease real estate funds have delivered strong risk-adjusted returns relative to both balanced property funds (with shorter lease terms) and the wider property market. This relative performance has been particularly strong when wider property market performance has been weak. Long lease funds have objectives aligned with liability matching and their performance suggests they are lower risk (more bond-like) investments. In addition, our analysis highlights they are far less responsive to the wider property market than balanced funds. However, they are not significantly different from balanced property funds in terms of their short-term relationship with gilt yield movements.Practical implicationsFor pension funds and other investors the paper highlights that long lease real estate funds offer a different exposure than balanced property funds. Long lease funds have objectives more closely aligned to the overall objectives for pension fund investment but are not significantly more reliable than balanced property funds in the short-term as a liability hedge. For real estate fund managers, occupiers, developers and others active in the real estate market, the paper highlights why these funds have been (and are likely to remain) attractive to investors leading to substantial demand for long lease real estate investments.Originality/valueThis is the first study to review this increasingly important part of the UK real estate fund universe.

Artificial intelligence algorithms to predict Italian real estate market prices

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Luca Rampini ◽  
Fulvio Re Cecconi
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Real Estate ◽  
House Prices ◽  
Housing Prices ◽  
Real Estate Market ◽  
Content Type ◽  
Two Cities ◽  
Artificial Neural

PurposeThe assessment of the Real Estate (RE) prices depends on multiple factors that traditional evaluation methods often struggle to fully understand. Housing prices, in particular, are the foundations for a better knowledge of the Built Environment and its characteristics. Recently, Machine Learning (ML) techniques, which are a subset of Artificial Intelligence, are gaining momentum in solving complex, non-linear problems like house price forecasting. Hence, this study deployed three popular ML techniques to predict dwelling prices in two cities in Italy.Design/methodology/approachAn extensive dataset about house prices is collected through API protocol in two cities in North Italy, namely Brescia and Varese. This data is used to train and test three most popular ML models, i.e. ElasticNet, XGBoost and Artificial Neural Network, in order to predict house prices with six different features.FindingsThe models' performance was evaluated using the Mean Absolute Error (MAE) score. The results showed that the artificial neural network performed better than the others in predicting house prices, with a MAE 5% lower than the second-best model (which was the XGBoost).Research limitations/implicationsAll the models had an accuracy drop in forecasting the most expensive cases, probably due to a lack of data.Practical implicationsThe accessibility and easiness of the proposed model will allow future users to predict house prices with different datasets. Alternatively, further research may implement a different model using neural networks, knowing that they work better for this kind of task.Originality/valueTo date, this is the first comparison of the three most popular ML models that are usually employed when predicting house prices.

Determinants of foreign and domestic non-listed real estate fund flows in India

2020 ◽  
Vol 38 (6) ◽  
pp. 503-524
Author(s):  
Ashish Gupta ◽  
Graeme Newell ◽  
Deepak Bajaj ◽  
Satya Mandal
Keyword(s):  
Time Series ◽  
Real Estate ◽  
Time Series Data ◽  
Real Estate Market ◽  
Series Data ◽  
Fund Flows ◽  
Content Type ◽  
Empirical Results ◽  
Distributed Lag ◽  
Macroeconomic Determinants

PurposeReal estate forms an important part of any economy and the investment in real estate, in turn, is impacted by the macroeconomic environment of that country. The purpose of the present research is to examine macroeconomic determinants of foreign and domestic non-listed real estate fund (NREF) flows and to examine whether they are similar or different for an emerging economy like India.Design/methodology/approachThe long and short-run cointegration between the time-series variables is estimated using the autoregressive distributed lag (ARDL) bounds test and error correction model (ECM) using quarterly data across the 2005–2017 period. ARDL is a suitable method for short time-series data.FindingsThe empirical results indicate that domestic NREF flows are positively and significantly impacted by real GDP and performance of listed real estate stocks (i.e. BSE realty index). Whereas, foreign NREF flows are positively and significantly impacted by the exchange rate, performance of listed real estate stocks and domestic NREF flows.Practical implicationsThe empirical results have significant implications for academicians, policy makers and real estate market practitioners. In the context of these results, some interesting insights are gained that would help in the implementation of the policies aimed toward increasing the fund flows in the real estate sector, which in turn would have a significant trickle-down effect on the Indian economy.Originality/valueThe existing literature looks at macroeconomic and other drivers of foreign investment in international real estate investments. However, there are very few studies on the determinants of domestic real estate investment flows and on determinants of NREFs' investment flows; particularly in emerging markets. The present study, in contrast, evaluates simultaneously the macroeconomic determinants of the domestic and foreign NREFs' investment flows in India. The ARDL and ECM method used has been applied for the first time to the study of NREFs.

Predicting property price index using artificial intelligence techniques

2019 ◽  
Vol 12 (6) ◽  
pp. 1072-1092 ◽  
Author(s):  
Rotimi Boluwatife Abidoye ◽  
Albert P.C. Chan ◽  
Funmilayo Adenike Abidoye ◽  
Olalekan Shamsideen Oshodi
Keyword(s):  
Artificial Intelligence ◽  
Real Estate ◽  
Price Index ◽  
Policy Formation ◽  
Support Vector ◽  
Ann Model ◽  
Property Market ◽  
Content Type ◽  
Property Prices ◽  
Property Price

Purpose Booms and bubbles are inevitable in the real estate industry. Loss of profits, bankruptcy and economic slowdown are indicators of the adverse effects of fluctuations in property prices. Models providing a reliable forecast of property prices are vital for mitigating the effects of these variations. Hence, this study aims to investigate the use of artificial intelligence (AI) for the prediction of property price index (PPI). Design/methodology/approach Information on the variables that influence property prices was collected from reliable sources in Hong Kong. The data were fitted to an autoregressive integrated moving average (ARIMA), artificial neural network (ANN) and support vector machine (SVM) models. Subsequently, the developed models were used to generate out-of-sample predictions of property prices. Findings Based on the prediction evaluation metrics, it was revealed that the ANN model outperformed the SVM and ARIMA models. It was also found that interest rate, unemployment rate and household size are the three most significant variables that could influence the prices of properties in the study area. Practical implications The findings of this study provide useful information to stakeholders for policy formation and strategies for real estate investments and sustained growth of the property market. Originality/value The application of the SVM model in the prediction of PPI in the study area is lacking. This study evaluates its performance in relation to ANN and ARIMA.

Energy performance certificates in the Turin real estate market

2017 ◽  
Vol 10 (2) ◽  
pp. 149-169 ◽  
Author(s):  
Elena Fregonara ◽  
Diana Rolando ◽  
Patrizia Semeraro
Keyword(s):  
Real Estate ◽  
House Prices ◽  
Energy Performance ◽  
Real Estate Market ◽  
Market Liquidity ◽  
Hedonic Model ◽  
Price Variation ◽  
Content Type ◽  
Time On The Market ◽  
The Impact

Purpose The purpose of this paper is to assess the impact of the Energy Performance Certificate (EPC) on the Italian real estate market, focusing on old buildings. The contribution of EPC labels to house prices and to market liquidity was measured to analyze different aspects of the selling process. Design/methodology/approach A traditional hedonic model was used to explain the variables of listing price, transaction price, time on the market and bargaining outcome. In addition to EPC labels, the building construction period and the main features of apartments were included in the model. A sample of 879 transactions of old properties in Turin in 2011-2014 was considered. Findings A first hedonic model let us suppose that low EPC labels (E, F and G) were priced in the market although EPC labels explained only 6-8 per cent of price variation. A second full hedonic model, which included apartment characteristics, revealed that EPC labels had no impact on prices. Originality/value In Italy EPC has been mandatory for house transactions since 2009, so there are few studies on the effect of EPC on the Italian real estate market at least to our knowledge. Furthermore, unusually for the Italian context, in this paper also transaction prices were analyzed, in addition to the more frequently used listing prices.

Downturn in Greece and abroad will sap property market

2020 ◽  
Keyword(s):  
Real Estate ◽  
Real Estate Market ◽  
Economic Downturn ◽  
Property Market ◽  
Content Type ◽  
The Real Estate ◽  
Large Cities ◽  
The Real Estate Market ◽  
Push Down ◽  
First Time

Significance This second extension is due to a slower-than-expected fall in cases in the COVID-19 pandemic’s second wave: 904 new infections were reported in the previous 24 hours yesterday, the first time since October 26 that daily cases have fallen below 1,000. The lockdown’s restrictions on economic activity threaten to reverse the nascent economic recovery, including in the real estate market. Impacts An economic downturn in investors’ home markets could dampen demand for Greek properties. The volumes of non-performing loans secured by real estate are expected to rise along with increased corporate insolvencies. An increased supply of properties for long-term residential rentals will push down rents in large cities.

scholarly journals Pricing risk and its use in modelling real estate market yields

2020 ◽  
Vol 38 (5) ◽  
pp. 419-433
Author(s):  
Tony McGough ◽  
Jim Berry
Keyword(s):  
Real Estate ◽  
Global Financial Crisis ◽  
Real Estate Market ◽  
Commercial Real Estate ◽  
Government Bonds ◽  
Content Type ◽  
Real Estate Markets ◽  
Market Sentiment ◽  
The Global Financial Crisis ◽  
Risk Measurements

Purpose In the light of past financial and economic turmoil, there has been a marked increase in the volatility in real estate markets. This has impacted on the pricing of property assets, partly through market sentiment and particularly concerning risk. It also limits modelling accuracy model accuracy. The purpose of this paper is to create a new variable and model to enhance analysis of what drives real estate yields incorporating market sentiment to risk. Design/methodology/approach This paper specifically considers the modelling of property pricing within a volatile economic environment. The theoretical context begins by analysing the relationship between property yields and government bonds. The analytical context then moves on to specifically include a measurement of risk which stresses its role and importance in investment markets since the Global Financial Crisis. The model thus incorporates macroeconomic and real estate data, together with an international risk multiplier, which is calculated within the paper. Findings The paper finds the use of measurements of market sentiment and risk are more powerful tools for modelling yields than previous techniques alone. Research limitations/implications This is an initial paper outlining the creation of sentiment and risk measurements in the financial market and showing an example of its application to a commercial real estate market. The implication is that this could add a major new explanatory variable to modelling of yields. Practical implications The paper highlights the importance of risk in the pricing of commercial real estate, over and above normal variables. It highlights how this can help explain over and undershooting of yields within commercial real estate which would be of great importance in the investment world. Originality/value This paper attempts to explicitly measure market sentiment, pricing of risk and how this impacts real estate pricing.

scholarly journals Market maturity: China commercial real estate market

2015 ◽  
Vol 33 (1) ◽  
pp. 4-18 ◽  
Author(s):  
Qiulin Ke ◽  
Karen Sieracki
Keyword(s):  
Real Estate ◽  
Emerging Market ◽  
Evolutionary Process ◽  
Real Estate Market ◽  
Commercial Real Estate ◽  
Property Market ◽  
Content Type ◽  
Commercial Property ◽  
High Government ◽  
International Investors

Purpose – The purpose of this paper is to explore the evolutionary path to market maturity that China property market has taken over the last few decades. The focus is on the commercial real estate markets in Beijing and Shanghai. It will help international investors understand the market environment, risk and market activity process. Design/methodology/approach – In this research, the authors apply the market maturity framework and its key determinants based on previous work undertaken by Keogh and D’Arcy (1994) and Chin et al. (2006) for the analysis of Chinese commercial property market. Particular focus is on Beijing and Shanghai. The questionnaire is designed to obtain fair and objective views from international property consultancy firms active in Beijing and Shanghai markets. There are not many of these international property consultancies. The reason why this type of business was selected was to insure that the business had an understanding of China’s place in the global commercial real estate market as this market matures from its emerging market status. Findings – The findings reveal that the respondents felt the commercial property markets in Shanghai and Beijing were now moderately mature. However, issues such as poorer level of standard market information, development instability, low transparency of the legal system, high taxes and high government invention still existed in China’s commercial property market, therefore hindering its progress towards greater market maturity. Research limitations/implications – The small same size of the survey is the major limitation of the research. Practical implications – International investors and analysts can benefit from the research findings through a better understanding of the behaviour and trends in this unique market which will be reflected in their decision-making process. Originality/value – An explorative approach was used due to the lack of data to examine the perception of China’s commercial property market’s evolution and maturity. The findings can then be placed in the context of other Southeast Asian cities. The evolutionary process of China’s property market is rarely examined in previous studies of China property market due to the lack of data and transparency.

Sign in / Sign up

Export Citation Format

Share Document