Interpretable Machine Learning for Real Estate Market Analysis

40 Pages Posted: 29 Apr 2021

See all articles by Felix Lorenz

Felix Lorenz

University of Regensburg - International Real Estate Business School (IREBS)

Jonas Willwersch

University of Regensburg - International Real Estate Business School (IREBS)

Marcelo Cajias

PATRIZIA AG; Universität Regensburg

Franz Fuerst

University of Cambridge - Department of Land Economy; University of Melbourne; City University of New York - Center for Urban Research

Date Written: April 28, 2021

Abstract

While Machine Learning (ML) excels at predictive tasks, its inferential capacity is limited due to its complex non-parametric structure. This paper aims to elucidate the analytical behavior of ML through Interpretable Machine Learning (IML) in a real estate context. Using a hedonic ML approach to predict unit-level residential rents for Frankfurt, Germany, we apply a set of model-agnostic interpretation methods to decompose the rental value drivers and plot their trajectories over time. Living area and building age are the strongest predictors of rent, followed by proximity to CBD and neighborhood amenities. Our approach is able to detect the critical distances to these centers beyond which rents tend to decline more rapidly. Conversely, close proximity to hospitality facilities as well as public transport is associated with rental discounts. Overall, our results suggest that IML methods provide insights into algorithmic decision-making by illustrating the relative importance of hedonic variables and their relationship with rental prices in a dynamic perspective.

Keywords: Interpretable Machine Learning, Microeconomic Hedonic Pricing, Housing Markets, Rental Markets

JEL Classification: D14, G12, R31

Suggested Citation

Lorenz, Felix and Willwersch, Jonas and Cajias, Marcelo and Fuerst, Franz, Interpretable Machine Learning for Real Estate Market Analysis (April 28, 2021). Available at SSRN: https://ssrn.com/abstract=3835931 or http://dx.doi.org/10.2139/ssrn.3835931

Felix Lorenz

University of Regensburg - International Real Estate Business School (IREBS) ( email )

Universitaetsstrasse 31
Regenburg, Bavaria 93040
Germany

Jonas Willwersch

University of Regensburg - International Real Estate Business School (IREBS) ( email )

Universitaetsstrasse 31
Regenburg, Bavaria 93040
Germany

Marcelo Cajias

PATRIZIA AG ( email )

Fuggerstr. 26
Augsburg, 86150
Germany
+49 (0) 151 17215198 (Phone)

HOME PAGE: http://www.patrizia.ag

Universität Regensburg ( email )

93040 Regensburg
D-93040 Regensburg, 93053
Germany

Franz Fuerst (Contact Author)

University of Cambridge - Department of Land Economy ( email )

19 Silver Street
Cambridge, CB3 9EP
United Kingdom

HOME PAGE: http://www.landecon.cam.ac.uk/directory/dr-franz-fuerst

University of Melbourne ( email )

185 Pelham Street
Carlton, Victoria 3053
Australia

City University of New York - Center for Urban Research

CUNY The Graduate Center
New York, NY 10011
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
286
Abstract Views
1,008
Rank
193,482
PlumX Metrics