Search results

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).

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.

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.

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.

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.

The purpose of this paper is to examine the market liquidity (time-on-market (TOM)) and its determinants, for rental dwellings in the largest seven German cities, with big data.

The determinants of TOM are estimated with the Cox proportional hazards model. Hedonic characteristics, as well as socioeconomic and spatial variables, are combined with different fixed effects and controls for non-linearity, so as to maximise the explanatory power of the model.

Higher asking rent and larger living space decrease the liquidity in all seven markets, while the age of a dwelling, the number of rooms and proximity to the city centre accelerate the letting process. For the other hedonic characteristics heterogeneous implications emerge.

The findings are of interest for institutional and private landlords, as well as governmental organisations in charge of housing and urban development.

This is the first paper to deal with the liquidity of rental dwellings in the seven most populated cities of Europe’s second largest rental market, by applying the Cox proportional hazards model with spatial gravity variables. Furthermore, the German rental market is of particular interest, as approximately 60 per cent of all rental dwellings are owned by private landlords and the German market is organised polycentrically.

Digitalisation and AI are the most intensively discussed topics in the real estate industry. The subject aims at increasing the efficiency of existing processes and the institutional side of the industry is really interested. And in some ways, this is a breakthrough. This article elaborates on the current status quo and future path of the industry.

The real estate industry is evolving, and parts of the business are increasingly being conquered by “proptechs” and “fintechs”. They have come into real estate to stay not because they discovered inefficiencies in the way one manages and does business with real estate, but because they come with an arsenal of new technologies that can change the whole game. The article discusses a path for changing the game in real estate.

“location, location, location” has now evolved to “data, data, data”. However, there is one essential aspect that must be considered before the latter can become the real value creator: the ability of market players to analyse data. And this does not mean being an excellent Excel user. The near future sees a solution called Explainable Artificial Intelligence (XAI) meaning that the econometric world constructed decades ago has an expiry date.

One needs to delete two myths from their mind: data quantity is proportional to accurate insights and that bringing your data to a cloud will deliver you with all the insights your business needs almost immediately.

This paper aims to explore the in-sample explanatory and out-of-sample forecasting accuracy of the generalized additive model for location, scale and shape (GAMLSS) model in contrast to the GAM method in Munich’s residential market.

The paper explores the in-sample explanatory results via comparison of coefficients and a graphical analysis of non-linear effects. The out-of-sample forecasting accuracy focusses on 50 loops of three models excluding 10 per cent of the observations randomly. Afterwards, it obtains the predicted functional forms and predicts the remaining 10 per cent. The forecasting performance is measured via error variance, root mean squared error, mean absolute error and the mean percentage error.

The results show that the complexity of asking rents in Munich is more accurately captured by the GAMLSS approach than the GAM as shown by an outperformance in the in-sample explanatory accuracy. The results further show that the theoretical and empirical complexities do pay off in view of the increased out-of-sample forecasting power of the GAMLSS approach.

The computational requirements necessary to estimate GAMLSS models in terms of number of cores and RAM are high and might constitute one of the limiting factors for (institutional) researchers. Moreover, large and detailed knowledge on statistical inference and programming is necessary.

The usage of the GAMLSS approach would lead policymakers to better understand the local factors affecting rents. Institutional researchers, instead, would clearly aim at calibrating the forecasting accuracy of the model to better forecast rents in investment strategies. Finally, future researchers are encouraged to exploit the large potential of the GAMLSS framework and its modelling flexibility.

The GAMLSS approach is widely recognised and used by international institutions such as the World Health Organisation, the International Monetary Fund and the European Commission. This is the first study to the best of the author’s knowledge to assess the properties of the GAMLSS approach in applied real estate research from a statistical asymptotic perspective by using a unique data basis with more than 38,000 observations.

The paper shows with two concrete examples about how algorithms are used in active real estate management. The paper also highlights that the discussion about the adoption of new technologies is crucial for market players.

The authors review the current status quo about new technologies in real estate and provide two examples of how algorithms can be used to understand locations and the value drivers of rents.

Location, location, location is nowadays data, data, data coupled with the knowledge of how to create life out of data. Algorithm can help to understand the value drivers of rents and can also help to evaluate the attractiveness of a location.

Real estate management will adapt to new technologies fast. This change has the potential to disrupt exiting strategies due to the increase in efficiency, insights, transparency and location knowledge. Investment managers walking this talk will definitely benefit in future.

The paper makes usage of the latest machine learning technologies applied to real estate investment cases. This is a unique opportunity on bringing light on the discussion about transparency in real estate.

The real estate industry is known as a late adopter when it comes to changes and innovations. While the industry is slowly evolving, parts of the sector are increasingly being conquered by property-related start-ups, known as “PropTechs”. These companies offer solutions and cutting-edge technologies to increase efficiencies and solve industry-wide problems. However, little is known about these companies' survival. This paper analyses the survival rate of PropTech firms and the determinants.

Based on a sample of 1,052 firms, factors that influence the firms' survival rate are analysed using the Cox Proportional Hazards Model, which is expanded with non-linear splines to capture turning points in the survival.

The authors find that in addition to the size, financing condition plays the most critical role in the success of Prop-Tech firms, including the number of financing rounds and maximum number of investors over lifetime. Moreover, the relationships are non-linear. Founding years and technology focus can also statistically influence the success rate. Companies founded before 2008 focussing on Sustainability Technology, Data and Business Analytics, Real Estate-related FinTech and Visualisation show the highest success rates.

The results are critical for investors interested in PropTechs to understand the success of their investments better. The importance of financing conditions shows that both investors and PropTechs may benefit from better financing processes that provide funds in a timelier manner.

The authors exploit a new and comprehensive data set that includes over 6,000 PropTechs globally. The authors' study fills in the literature gap on the determinants of the survival rate of PropTechs.

Commercial real estate and office rental values, in particular, have long been the focus of research. Several forecasting frameworks for office rental values in multivariate and univariate fashions have been proposed. Recent developments in time series forecasting using machine learning and deep learning methods offer an opportunity to update traditional univariate forecasting frameworks.

With the aim to extend research on univariate rent forecasting a hybrid methodology combining both ARIMA and a neural network model is proposed to exploit the unique strengths of both methods in linear and nonlinear modelling. N-BEATS, a deep learning algorithm that has demonstrated state-of-the-art forecasting performance in major forecasting competitions, are explained. With the ARIMA model, it is jointly applied to the office rental dataset to produce forecasts for four-quarters ahead.

When the approach is applied to a dataset of 21 major European office cities, the results show that the ensemble model can be an effective approach to improve the prediction accuracy achieved by each of the models used separately.

Real estate forecasting is essential for assessing the value of managing portfolios and for evaluating investment strategies. The approach applied in this paper confirms the heterogeneity of real estate markets. The application of mixed modelling via linear and nonlinear methods decreases the uncertainty of abrupt changes in rents.

To the best of the authors' knowledge, no such application of a hybrid model updating classical statistical forecasting with a deep learning neural network approach in the field of commercial real estate rent forecasting has been undertaken.

This paper aims to develop a conceptual understanding and a methodological approach for calculating residential net initial yields for both a buy-to-hold and rental investment strategy from hedonic models.

The markets modelled comprehend of dwellings for rent and sell in Germany. For each of them, two regression models are estimated to extract implicit prices and rents for an artificial identical dwelling and estimate the willingness to pay for the same asset from both a buy-to-hold and rental investment strategy.

The 3,381 estimated net initial yields in the 161 German markets showed a spatial pattern with the biggest and most attractive cities showing the lowest yields and a self-adjusting process in the markets surrounding the top cities. The net initial yields over time show that prices have increased stronger than rents, leading to rock bottom yields for residential assets and a significant premium in comparison to government bond yields. The approach responds to the spatial hierarchy of markets in Germany, meaning that the level of the estimated yields is accurate and achievable from an investment perspective.

The investment case in residential markets is certainly unique as net initial yields are scarce, especially due to the relatively low number of investment comparables. The paper sheds light on this problem from a conceptual and methodological perspective and confirms that investment yields are deducible by making usage of hedonic models and big data.

In the era of digitalization and big data, residential assets are mostly brought to the market via digital multiple listing systems. Transparency is an essential barrier when assessing the pricing conditions of markets and deriving investment decisions. Although international brokers do provide detailed investment comparables on – mostly commercial – real estate markets, the residential sector remains a puzzle when it comes to investment yields. The paper sheds light on this problem.

This is the first article to apply a machine learning approach to the analysis of time on market on real estate markets.

The random survival forest approach is introduced to the real estate market. The most important predictors of time on market are revealed and it is analyzed how the survival probability of residential rental apartments responds to these major characteristics.

Results show that price, living area, construction year, year of listing and the distances to the next hairdresser, bakery and city center have the greatest impact on the marketing time of residential apartments. The time on market for an apartment in Munich is lowest at a price of 750 € per month, an area of 60 m2, built in 1985 and is in a range of 200–400 meters from the important amenities.

The findings might be interesting for private and institutional investors to derive real estate investment decisions and implications for portfolio management strategies and ultimately to minimize cash-flow failure.

Although machine learning algorithms have been applied frequently on the real estate market for the analysis of prices, its application for examining time on market is completely novel. This is the first paper to apply a machine learning approach to survival analysis on the real estate market.