Artificial Neural Network, Quantile and Semi-Log Regression Modelling of Mass Appraisal in Housing

We used a large sample of 188,652 properties, which represented 4.88% of the total housing stock in Catalonia from 1994 to 2013, to make a comparison between different real estate valuation methods based on artificial neural networks (ANNs), quantile regressions (QRs) and semi-log regressions (SLRs). A literature gap in regard to the comparison between ANN and QR modelling of hedonic prices in housing was identified, with this article being the first paper to include this comparison. Therefore, this study aimed to answer (1) whether QR valuation modelling of hedonic prices in the housing market is an alternative to ANNs, (2) whether it is confirmed that ANNs produce better results than SLRs when assessing housing in Catalonia, and (3) which of the three mass appraisal models should be used by Spanish banks to assess real estate. The results suggested that the ANNs and SLRs obtained similar and better performances than the QRs and that the SLRs performed better when the datasets were smaller. Therefore, (1) QRs were not found to be an alternative to ANNs, (2) it could not be confirmed whether ANNs performed better than SLRs when assessing properties in Catalonia and (3) whereas small and medium banks should use SLRs, large banks should use either SLRs or ANNs in real estate mass appraisal.

The spatial dimension of the French private rental markets: Evidence from microgeographic data in 2015

This article draws on data collected by local rental observatories in 12 French urban units in 2015 to analyze the spatial dimension of hedonic rental prices in the private rental market through (i) the spatial heterogeneity between urban units and (ii) the wide variety of contextual and locational characteristics (socio-economic, environmental (dis)amenity, and accessibility) and flexible specifications to capture their potential non-linear influence on rent. Based on a joint test of equality of coefficients across all urban units, we find that hedonic prices differ for 75% of the characteristics, thereby justifying a detailed analysis of heterogeneity. Lyon, Nice, and Paris taken individually are the urban units with the most specific valuations of housing characteristics and socio-economic characteristics. Our analysis reveals that housing characteristics, median income, and distance to the center are clearly the variables with the most heterogeneous effects on hedonic prices.

What’s so special about character?

Special Character Areas (SCAs) in Auckland, New Zealand, are areas with distinctive aesthetic, physical and visual qualities. Preservation policies entail controls on the design and appearance of new buildings, and on demolition, additions and alterations to existing buildings. To promote densification of the city, the Auckland Unitary Plan (AUP) removed SCA preservation rules in certain areas. This article assesses the trade-off between SCA preservation and housing development. We employ hedonic prices models to about 85,000 sale transactions between 2012 and 2016 and find that in 2012, the SCA price premium was 11.4% whereas the premium on upzoned properties (those with increased development allowances under the AUP) was zero. Over time, the SCA premium decreases, and by 2016 it was down to about 4.3%. At the same time, upzoning premiums increased to about 5% in 2016. These results reveal a demand shift from the protections of SCA towards flexibility on the development options of land.

Income capitalisation method and hedonic model: an integrated approach

Purpose The purpose of this paper is to provide an integrated approach that combines the two methods usually used in the real estate appraisals, namely, the income capitalisation method and the hedonic model. Design/methodology/approach In order to pull out the link between the income capitalisation approach and the hedonic model, the standard hedonic price function is introduced into the basic model of income capitalisation instead of the house market value. It follows that, from the partial derivative, a direct relation between hedonic prices and discount rate can be obtained. Finally, by using the close relationship between income capitalisation and direct capitalisation, a mathematical relation between hedonic prices and capitalisation rate is also obtained. Findings The developed method allows to estimate the capitalisation rate using only hedonic prices. Indeed, selling and hedonic prices incorporate all of the information required to correctly estimate the capitalisation rate. Furthermore, given the close relation among going-in and going-out capitalisation rates and discount rate, the proposed method could also be useful for determining both the going-out capitalisation rate and the discount rate. Practical implications Obviously, it is always preferable to estimate the capitalisation rate by just using comparable transactional data. Nevertheless, the method developed in this paper is especially useful when: the rental income data are missing and/or not entirely reliable; the data on rental income and house price are related to different homes; the capitalisation rate, in fact, should compare the rent and value of identical homes. In these cases, therefore, the method can be a valuable alternative to direct estimation. Originality/value The large and important literature on real estate economics and real estate appraisal neglects the relationship between hedonic prices and capitalisation rate, thus considering the hedonic model and the income capitalisation approach as two separate and alternative methods. This paper, instead, shows that integration is possible and relatively simple.

Does the law of one price hold for hedonic prices?

Hedonic prices of locational attributes in urban land markets are determined by a process of spatial arbitrage that is similar to that which underpins the law of one price. If hedonic prices deviate from their spatial equilibrium values then individuals can benefit from changing locations. I examine whether the law holds for the hedonic price of rail access using a unique historical dataset for Berlin over the period 1890–1914, characterised by massive investment in the transport infrastructure. I estimate the hedonic price of rail access across multiple urban neighbourhoods and time periods to generate a panel dataset of hedonic price differences that I test for stationarity using a panel unit root test. Across multiple specifications I consistently fail to reject the null hypothesis of no unit root and accept the alternative hypothesis that the law holds. My estimates indicate a half-life for convergence to the law of one price that lies between 0.28 and 1.14 years. This result is consistent with spatial equilibrium.