Purpose: The purpose of this paper is to investigate the effect of energy consumption on the financial performance of German residential buildings in a large panel framework. The authors provide evidence that energy efficiency in the residential sector is a relevant factor affecting both tenant investment decisions and consequently the performance of investor portfolios.Design/methodology/approach: Based on the IPD Database and information from the German statistical office, the authors create portfolios of buildings across several energy consumption levels in order to describe the energy pricing mechanism in the context of total return and rent price. Furthermore, the authors apply conditional and unconditional regressions over the period of 2008 and 2010, to accurately quantify the energy price premium in the German residential market.Findings: The descriptive portfolio results show that energy‐efficient buildings yield an up to 3.15 percent higher return and 0.76 €/m² higher rent than inefficient buildings. Furthermore, the regression results indicate that a one percent decline in energy consumption affects the total return of buildings positively by +0.015 percent. The hedonic results additionally show that one percent energy conservation boosts rent prices by +0.08 percent and market value by +0.45 percent, ceteris paribus.Originality/value: Overall, the study presents an alternative methodology for describing and estimating hedonic datasets and offers some initial empirical evidence on the energy price premium in German residential markets. The paper contributes to prior European studies regarding the use and implications of energy performance certificates and confirms their significant impact on residential housing performance variables.

Machine Learning (ML) excels at most predictive tasks but its complex nonparametric structure renders it less useful for inference and out‐of sample predictions. This article aims to elucidate and enhance the analytical capabilities of ML in real estate through Interpretable ML (IML). Specifically, we compare a hedonic ML approach to a set of model‐agnostic interpretation methods. Our results suggest that IML methods permit a peek into the black box of algorithmic decision making by showing the web of associative relationships between variables in greater resolution. In our empirical applications, we confirm that size and age are the most important rent drivers. Further analysis reveals that certain bundles of hedonic characteristics, such as large apartments in historic buildings with balconies located in affluent neighborhoods, attract higher rents than adding up the contributions of each hedonic characteristic. Building age is shown to exhibit a U‐shaped pattern in that both the youngest and oldest buildings attract the highest rents. Besides revealing valuable distance decay functions for spatial variables, IML methods are also able to visualise how the strength and interactions of hedonic characteristics change over time, which investors could use to determine the types of assets that perform best at any given stage of the real estate investment cycle.

This paper investigates the relationship between corporate social and environmental performance and financial performance for a sample of publicly traded US real estate companies. Using the MSCI ESG (formerly KLD) database on seven Environmental, Social & Governance dimensions in the 2003–2010 period, and weighting the dimensions according to prominence in the real estate sector, we model Tobin's Q and annual total return in a panel data framework. The results indicate a positive relationship between ESG rating and Tobin's Q but this effect is driven by ESG concerns rather than strengths. Consistently across all model specifications, overall ESG ratings are associated with lower returns. Negative scores appear to result in higher returns, at least in the short run, but positive scores have no significant impact on returns.

Data-driven machine learning algorithms have initiated a paradigm shift in hedonic house price and rent modeling through their ability to capture highly complex and non-monotonic relationships. Their superior accuracy compared to parametric model alternatives has been demonstrated repeatedly in the literature. However, the statistical independence of the data implicitly assumed by resampling-based error estimates is unlikely to hold in a real estate context as price-formation processes in property markets are inherently spatial, which leads to spatial dependence structures in the data. When performing conventional cross-validation techniques for model selection and model assessment, spatial dependence between training and test data may lead to undetected overfitting and overoptimistic perception of predictive power. This study sheds light on the bias in cross-validation errors of tree-based algorithms induced by spatial autocorrelation and proposes a bias-reduced spatial cross-validation strategy. The findings confirm that error estimates from non-spatial resampling methods are overly optimistic, whereas spatially conscious techniques are more dependable and can increase generalizability. As accurate and unbiased error estimates are crucial to automated valuation methods, our results prove helpful for applications including, but not limited to, mass appraisal, credit risk management, portfolio allocation and investment decision making.

Purpose: A green agenda has become a growing subject throughout an increasing number of European listed real estate companies over the last decade. The focus on sustainability is presumably not only goodwill or legislation driven but is rather a benefit driven action to achieve an economic surplus. The purpose of this paper is the development of an adequate sustainability definition, the investigation of the effect of a sustainability agenda on a company level, and the identification of possible financial benefits.Design/methodology/approach: This is an explorative qualitative and quantitative study. First, the authors developed a four‐bottom‐line real estate sustainability agenda in accordance with the guidelines of the European Public Real Estate Association and the Global Reporting Initiative. Second, the study examines 80 European listed real estate companies from 2006 until 2009, and third, the study applies a panel analysis with conditional and unconditional regression techniques.Findings: After classifying firms across different levels of sustainability intensity and quantifying the impact of an intensive green agenda the authors found a positive linkage between a green agenda and a green performance, especially in terms of an increased ability to generate revenues and a decreased level of idiosyncratic stock volatility. As a result, green commitments are not merely altruisms but are economically driven instead.Originality/value: This paper gives, to the authors' knowledge, a first insight of how European real estate listed companies behave in terms of corporate social responsibility. The study contributes to the theoretical literature of corporate sustainable real estate companies by establishing an economic transmission mechanism as well as providing empirical evidence in favour of responsible activities.