{"title":"Exploring the predictive power of ANN and traditional regression models in real estate pricing: evidence from Prishtina","authors":"Visar Hoxha","doi":"10.1108/jpif-06-2023-0051","DOIUrl":null,"url":null,"abstract":"Purpose The purpose of the study is to examine the efficiency of linear, nonlinear and artificial neural networks (ANNs), in predicting property prices. Design/methodology/approach The present study uses a dataset of 1,468 real estate transactions from 2020 to 2022, obtained from the Department of Property Taxes of Republic of Kosovo. Beginning with a fundamental linear regression model, the study tackles the question of overlooked nonlinearity, employing a similar strategy like Peterson and Flanagan (2009) and McCluskey et al . (2012), whereby ANN's predictions are incorporated as an additional regressor within the ordinary least squares (OLS) model. Findings The research findings underscore the superior fit of semi-log and double-log models over the OLS model, while the ANN model shows moderate performance, contrary to the conventional conviction of ANN's superior predictive power. This is notably divergent from the prevailing belief about ANN's superior predictive power, shedding light on the potential overestimation of ANN's efficacy. Practical implications The study accentuates the importance of embracing diverse models in property price prediction, debunking the notion of the ubiquitous applicability of ANN models. The research outcomes carry substantial ramifications for both scholars and professionals engaged in property valuation. Originality/value Distinctively, this research pioneers the comparative analysis of diverse models, including ANN, in the setting of a developing country's capital, hence providing a fresh perspective to their effectiveness in property price prediction.","PeriodicalId":46429,"journal":{"name":"Journal of Property Investment & Finance","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Property Investment & Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/jpif-06-2023-0051","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose The purpose of the study is to examine the efficiency of linear, nonlinear and artificial neural networks (ANNs), in predicting property prices. Design/methodology/approach The present study uses a dataset of 1,468 real estate transactions from 2020 to 2022, obtained from the Department of Property Taxes of Republic of Kosovo. Beginning with a fundamental linear regression model, the study tackles the question of overlooked nonlinearity, employing a similar strategy like Peterson and Flanagan (2009) and McCluskey et al . (2012), whereby ANN's predictions are incorporated as an additional regressor within the ordinary least squares (OLS) model. Findings The research findings underscore the superior fit of semi-log and double-log models over the OLS model, while the ANN model shows moderate performance, contrary to the conventional conviction of ANN's superior predictive power. This is notably divergent from the prevailing belief about ANN's superior predictive power, shedding light on the potential overestimation of ANN's efficacy. Practical implications The study accentuates the importance of embracing diverse models in property price prediction, debunking the notion of the ubiquitous applicability of ANN models. The research outcomes carry substantial ramifications for both scholars and professionals engaged in property valuation. Originality/value Distinctively, this research pioneers the comparative analysis of diverse models, including ANN, in the setting of a developing country's capital, hence providing a fresh perspective to their effectiveness in property price prediction.
期刊介绍:
Fully refereed papers on practice and methodology in the UK, continental Western Europe, emerging markets of Eastern Europe, China, Australasia, Africa and the USA, in the following areas: ■Academic papers on the latest research, thinking and developments ■Law reports assessing new legislation ■Market data for a comprehensive review of current research ■Practice papers - a forum for the exchange of ideas and experiences