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 methodsThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.
Purpose
The purpose of this study is to introduce a new perspective on determinants of cross-border investments in commercial real estate, namely, the relative attractiveness of a target market. So far, the literature has analyzed only absolute measures of investment attractiveness as determinants of cross-border investment flows.
Design/methodology/approach
The empirical study uses a classic ordinary least squares estimation for a European panel data set containing 28 cities in 18 countries, with quarterly observations from Q1/2008 to Q3/2018. After controlling for empirically proven explanatory covariates, the model is extended by the new relative measurement based on relative yields/cap rates and relative risk premia. Additionally, the study applies a generalized additive mixed model (GAMM) to investigate a potentially nonlinear relationship.
Findings
The study finds on average a ceteris paribus, statistically significant lagged influence of the proxy for relative attractiveness. Nonetheless, a differentiation is needed; relative risk premia are statistically significant, whereas relative yields are not. Moreover, the GAMM confirms a nonlinear relationship for relative risk premia and cross-border transaction volumes.
Practical implications
The results are of interest for both academia and market participants as a means of explaining cross-border capital flows. The existing knowledge on determinants is expanded by relative market attractiveness, as well as an awareness of nonlinear relationships. Both insights help to comprehend the underlying transaction dynamics in commercial real estate markets.
Originality/value
Whereas the existing body of literature focuses on absolute attractiveness to explain cross-border transaction activity, this study introduces relative attractiveness as an explanatory variable.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.