Improving property valuation accuracy: a comparison of hedonic pricing model and artificial neural network

Abstract Inaccuracies in property valuation is a global problem. This could be attributed to the adoption of valuation approaches, with the hedonic pricing model (HPM) being an example, that are inaccurate and unreliable. As evidenced in the literature, the HPM approach has gained wide acceptance among real estate researchers, despite its shortcomings. Therefore, the present study set out to evaluate the predictive accuracy of HPM in comparison with the artificial neural network (ANN) technique in property valuation. Residential property transaction data were collected from registered real estate firms domiciled in the Lagos metropolis, Nigeria, and were fitted into the ANN model and HPM. The results showed that the ANN technique outperformed the HPM approach, in terms of accuracy in predicting property values with mean absolute percentage error (MAPE) values of 15.94 and 38.23%, respectively. The findings demonstrate the efficacy of the ANN technique in property valuation, and if all the preconditions of property value modeling are met, the ANN technique is a reliable valuation approach that could be used by both real estate researchers and professionals.

[1]  V. Sampathkum,et al.  Evaluation of the Trend of Land Price using Regression and Neural Network Models , 2015 .

[2]  J. Brian Gray,et al.  Introduction to Linear Regression Analysis , 2002, Technometrics.

[3]  E. Hui,et al.  Measuring the neighboring and environmental effects on residential property value: Using spatial weighting matrix , 2007 .

[4]  S. Selim,et al.  Determinants of House Prices in Turkey : A Hedonic Regression Model , 2008 .

[5]  George A. Matysiak,et al.  Valuation uncertainty and the Mallinson Report , 1998 .

[6]  C. A. Ajayi,et al.  Variance in residential property valuation in Lagos, Nigeria , 2011 .

[7]  Marsela Thanasi.  Hedonic appraisal of apartments in Tirana , 2016 .

[8]  Rotimi Abidoye,et al.  Artificial neural network in property valuation: application framework and research trend , 2017 .

[9]  W. Shaw,et al.  Discontinued Operations Recognition, Initial Provisions, And Subsequent Adjustments , 2011 .

[10]  R. Cebula.  The Hedonic Pricing Model Applied to the Housing Market , 2009 .

[11]  H. White.  A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity , 1980 .

[12]  Margarita M. Lenk,et al.  An Exploration of Neural Networks and Its Application to Real Estate Valuation , 1995 .

[13]  Elaine Worzala,et al.  High‐tech valuation: should artificial neural networks bypass the human valuer? , 1997 .

[14]  Kwong Wing Chau,et al.  A Critical Review of Literature on the Hedonic Price Model , 2002 .

[15]  Jim Berry,et al.  Hedonic modelling, housing submarkets and residential valuation , 1996 .

[16]  M. Katz.  Validation of models , 2006 .

[17]  V. Limsombunchai.  House Price Prediction: Hedonic Price Model vs. Artificial Neural Network , 2004 .

[18]  Bioye Tajudeen Aluko,et al.  Examining valuer's judgement in residential property valuations in metropolitan Lagos, Nigeria , 2007 .

[19]  Albert T.P. So,et al.  Neural Network vs. Hedonic Price Model: Appraisal of High-Density Condominiums , 2002 .

[20]  V. Assimakopoulos,et al.  Real estate appraisal: a review of valuation methods , 2003 .

[21]  Jammalamadaka.  Introduction to Linear Regression Analysis (3rd ed.) , 2003 .

[22]  Stanley McGreal,et al.  Neural networks: the prediction of residential values , 1998 .

[23]  David McIlhatton,et al.  The Potential of Artificial Neural Networks in Mass Appraisal: The Case Revisited , 2012 .

[24]  Francis K. W. Wong,et al.  Causal relationship between construction activities, employment and GDP: The case of Hong Kong , 2015 .

[25]  Paulo J. G. Lisboa,et al.  The Use of Artificial Neural Networks in Decision Support in Cancer: a Systematic Review , 2005 .

[26]  Kostas S. Metaxiotis,et al.  Real estate valuation with artificial intelligence approaches , 2007, Int. J. Intell. Syst. Technol. Appl..

[27]  Hasan Selim,et al.  Determinants of house prices in Turkey: Hedonic regression versus artificial neural network , 2009, Expert Syst. Appl..

[28]  Tiesong Hu,et al.  A Modified Neural Network for Improving River Flow Prediction , 2005 .

[29]  S. Thomas Ng,et al.  A Modified Neural Network for Improving River Flow Prediction/Un Réseau de Neurones Modifié pour Améliorer la Prévision de L'Écoulement Fluvial , 2005 .

[30]  Rui Portocarrero Sarmento,et al.  Introduction to Linear Regression , 2017 .

[31]  M. Teixeira,et al.  Hedonic methodologies in the real estate valuation , 2010 .

[32]  Adelmo Luis Cechin,et al.  Real estate value at Porto Alegre city using artificial neural networks , 2000, Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks.

[33]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[34]  Julio Gallego Mora-Esperanza.  ARTIFICIAL INTELLIGENCE APPLIED TO REAL ESTATE VALUATION An example for the appraisal of Madrid , 2004 .

[35]  Paulo Cortez,et al.  Modeling wine preferences by data mining from physicochemical properties , 2009, Decis. Support Syst..

[36]  K. Lam,et al.  An Artificial Neural Network and Entropy Model for Residential Property Price Forecasting in Hong Kong , 2008 .

[37]  Christian Janssen,et al.  Robust estimation of hedonic models of price and income for investment property , 2001 .

[38]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[39]  J. Zurada,et al.  A Comparison of Regression and Artificial Intelligence Methods in a Mass Appraisal Context , 2011 .

[40]  Chunlu Liu,et al.  The effects of the late 2000s global financial crisis on Australia's construction demand , 2013 .

[41]  PIERLUIGI MORANO,et al.  Artificial intelligence in property valuations An application of artificial neural networks to housing appraisal , 2015 .

[42]  J. Andrew Ware,et al.  Residential property price time series forecasting with neural networks , 2002, Knowl. Based Syst..

[43]  S. Rosen.  Hedonic Prices and Implicit Markets: Product Differentiation in Pure Competition , 1974, Journal of Political Economy.

[44]  Satish Mohan,et al.  Effectiveness comparison of the residential property mass appraisal methodologies in the USA , 2011 .

[45]  J. N. Tabales,et al.  Artificial neural networks for predicting real estate prices , 2013 .

[46]  Jozef Zurada,et al.  Non-Conventional Approaches To Property Value Assessment , 2011 .

[47]  Barry Gilbertson,et al.  A vision for valuation , 2005 .

[48]  David McIlhatton,et al.  Prediction accuracy in mass appraisal: a comparison of modern approaches , 2013 .

[49]  Steffen P. Sebastian,et al.  Hedonic price indices for the Paris housing market , 2004 .

[50]  D. P. H. Tay,et al.  Artificial Intelligence and the Mass Appraisal of Residential Apartments , 1992 .

[51]  C.Y. Jim,et al.  Impacts of urban environmental elements on residential housing prices in Guangzhou (China) , 2006 .

[52]  F. Famuyiwa,et al.  Hedonic values of physical infrastructure in house rentals , 2014 .

[53]  Gurudeo Anand Tularam,et al.  PERFORMANCE OF MULTIPLE LINEAR REGRESSION AND NONLINEAR NEURAL NETWORKS AND FUZZY LOGIC TECHNIQUES IN MODELLING HOUSE PRICES , 2012 .

[54]  B. Hofmann,et al.  Bank Lending and Property Prices: Some International Evidence , 2003 .

[55]  Milton S. Boyd,et al.  Designing a neural network for forecasting financial and economic time series , 1996, Neurocomputing.

[56]  J. AdegokeO..  A study of valuation clients perception on mortgage valuation reliability , 2013 .

[57]  A. Owusu-Ansah.  Examination of the Determinants of Housing Values in Urban Ghana and Implications for Policy Makers , 2013 .

[58]  Rotimi Abidoye,et al.  A survey of property valuation approaches in Nigeria , 2016 .

[60]  M. Badics,et al.  Valuation Methods for the Housing Market: Evidence from Budapest , 2016 .