Comparing OLS based hedonic model and ANN in house price estimation using relative location

Author(s):  
Mudit D. Mankad
2019 ◽  
Vol 37 (3) ◽  
pp. 289-300
Author(s):  
Gaetano Lisi

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.


Author(s):  
Gaetano Lisi ◽  
Mauro Iacobini

The Italian housing market is characterised by both a strong heterogeneity of real estate assets and a reduced number of property sales. These features, indeed, hamper the use of the hedonic price method, namely, the method that is mostly used for assessing the house prices and for estimating the monetary value of housing characteristics. In this paper, therefore, a hedonic model with dummy variables that identify housing submarkets is used to achieve two important results: enabling greater use of multiple regression analysis in the study of the Italian real estate market, and catching, in the simplest possible manner, the effect of location on house price. Indeed, the house's location is, together with the area in square metres, the housing characteristic that most influences the house price.


2014 ◽  
Vol 587-589 ◽  
pp. 2285-2289
Author(s):  
Li Hui Rong ◽  
Yu Mei Sun

Housing is a typical kind of heterogeneity goods, namely each house contains a serious of different attributes and housing price is regarded as every attribute of comprehensive value judgment to family.Taking second-hand housing of Kunming city as the research object, this paper uses Hedonic model and WEB information to study the quantitative relationship between housing price and housing characteristic. The results show that semi-log form characteristic function fits the highest degree in second-hand housing of location attribute and the regression coefficient shows that residential link location is the largest factor affecting house price. Housing price influencing degree by residential property in turn is link location,rail traffic and property fees,volume rate,education facilities,bus line,decoration and construction area,and the main influence factors and influence degree of housing price vary from area to area.


2017 ◽  
Vol 0 (0) ◽  
Author(s):  
Adam W. Shao ◽  
Katja Hanewald ◽  
and Michael Sherris

AbstractHouse price indices are needed to assess house price risk in households’ portfolio allocation decisions and in many housing-related financial products such as reverse mortgages, mortgage insurance and real estate derivatives. This paper first introduces nine widely-used house price models to the insurance, risk management and actuarial literature and provides new evidence on the relative performance of these models. We then show how portfolio-level house price indices for properties with specific physical and locational characteristics can be constructed for these different models. All analyses are based on a large dataset of individual property transactions in Sydney, Australia, for the period 1971-2011. The unrestricted hedonic model and a hybrid hedonic repeat-sales model provide a good model fit and reliable portfolio-level house price indices. Our results are important for banks, insurers and investors that have exposure to house price risks.


2021 ◽  
Vol 207 ◽  
pp. 104016
Author(s):  
Cathrine Ulla Jensen ◽  
Toke Emil Panduro ◽  
Thomas Hedemark Lundhede ◽  
Kathrine von Graevenitz ◽  
Bo Jellesmark Thorsen

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Changro Lee ◽  
Key-Ho Park

PurposeMost prior attempts at real estate valuation have focused on the use of metadata such as size and property age, neglecting the fact that the building workmanship in the construction of a house is also a key factor for the estimation of house prices. Building workmanship, such as exterior walls and floor tiling correspond to the visual attributes of a house, and it is difficult to capture and evaluate such attributes efficiently through classical models like regression analysis. Deep learning approach is taken in the valuation process to utilize this visual information.Design/methodology/approachThe authors propose a two-input neural network comprising a multilayer perceptron and a convolutional neural network that can utilize both metadata and the visual information from images of the front view of the house.FindingsThe authors applied the two-input neural network to Guri City in Gyeonggi Province, South Korea, as a case study and found that the accuracy of house price estimations can be improved by employing image information along with metadata.Originality/valueFew studies considered the impact of the building workmanship in the valuation process. The authors revealed that it is useful to use both photographs and metadata for enhancing the accuracy of house price estimation.


Sign in / Sign up

Export Citation Format

Share Document