Estimation and updating methods for hedonic valuation

Abstract

Purpose The purpose of this paper is to investigate the accuracy and volatility of different methods for estimating and updating hedonic valuation models. Design/methodology/approach The authors apply six estimation methods (linear least squares, robust regression, mixed-effects regression, random forests, gradient boosting and neural networks) and two updating methods (moving and extending windows). They use a large and rich data set consisting of over 123,000 single-family houses sold in Switzerland between 2005 and 2017. Findings The gradient boosting method yields the greatest accuracy, while the robust method provides the least volatile predictions. There is a clear trade-off across methods depending on whether the goal is to improve accuracy or avoid volatility. The choice between moving and extending windows has only a modest effect on the results. Originality/value This paper compares a range of linear and machine learning techniques in the context of moving or extending window scenarios that are used in practice but which have not been considered in prior research. The techniques include robust regression, which has not previously been used in this context. The data updating allows for analysis of the volatility in addition to the accuracy of predictions. The results should prove useful in improving hedonic models used by property tax assessors, mortgage underwriters, valuation firms and regulatory authorities.

An analysis of papers published in theJournal of European Real Estate Research, 2008-2019

“…An example of a change that will affect most areas of real estate research is the disruption caused by the development of big data and artificial intelligence. Among other things, such development should have large impacts on property valuation (Zurada et al , 2011; McCluskey et al , 2013; Mayer et al , 2019), cities (Glaeser et al , 2018; Lim et al , 2018), corporate real estate (Ewert et al , 2018) and real estate analyses (Winson-Geideman et al , 2018; Bogin et al , 2019).…”

Hedonic Price for Amenities in Rural and Urban Residential Condominiums in Costa Rica

“…The first hedonic pricing model was developed to investigate the effect of surface area and distance from the city center on the price of agricultural land (Colwell & Dilmore, 1999;Haas, 1922). It is now recognized as a valuable tool for the appraisal and valuation of residential properties (Mayer et al, 2019). The hedonic pricing method is also applied to define the price of consumer goods, such as cars, according to the characteristics and condition of the object, as well as consumer preferences (Court, 1939;Cowling & Cubbin, 1972;Lancaster, 1966).…”

Editorial

“…We participated in that project by comparing the usefulness of hedonic, depreciated cost and “land leverage” techniques. One aim of the project was to focus on methods that can be implemented relatively easily in practice, so we did not consider more complex approaches such as machine learning (Mayer et al , 2019).…”