File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Predicting property prices with machine learning algorithms

TitlePredicting property prices with machine learning algorithms
Authors
KeywordsMachine Learning algorithms
SVM
RF
GBM
property valuation
Issue Date2021
PublisherRoutledge. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/09599916.asp
Citation
Journal of Property Research, 2021, v. 38 n. 1, p. 48-70 How to Cite?
AbstractThis study uses three machine learning algorithms including, support vector machine (SVM), random forest (RF) and gradient boosting machine (GBM) in the appraisal of property prices. It applies these methods to examine a data sample of about 40,000 housing transactions in a period of over 18 years in Hong Kong, and then compares the results of these algorithms. In terms of predictive power, RF and GBM have achieved better performance when compared to SVM. The three performance metrics including mean squared error (MSE), root mean squared error (RMSE) and mean absolute percentage error (MAPE) associated with these two algorithms also unambiguously outperform those of SVM. However, our study has found that SVM is still a useful algorithm in data fitting because it can produce reasonably accurate predictions within a tight time constraint. Our conclusion is that machine learning offers a promising, alternative technique in property valuation and appraisal research especially in relation to property price prediction.
DescriptionHybrid open access
Persistent Identifierhttp://hdl.handle.net/10722/294145
ISSN
2015 SCImago Journal Rankings: 0.489
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHo, WKO-
dc.contributor.authorTang, BS-
dc.contributor.authorWong, SW-
dc.date.accessioned2020-11-23T08:27:00Z-
dc.date.available2020-11-23T08:27:00Z-
dc.date.issued2021-
dc.identifier.citationJournal of Property Research, 2021, v. 38 n. 1, p. 48-70-
dc.identifier.issn0959-9916-
dc.identifier.urihttp://hdl.handle.net/10722/294145-
dc.descriptionHybrid open access-
dc.description.abstractThis study uses three machine learning algorithms including, support vector machine (SVM), random forest (RF) and gradient boosting machine (GBM) in the appraisal of property prices. It applies these methods to examine a data sample of about 40,000 housing transactions in a period of over 18 years in Hong Kong, and then compares the results of these algorithms. In terms of predictive power, RF and GBM have achieved better performance when compared to SVM. The three performance metrics including mean squared error (MSE), root mean squared error (RMSE) and mean absolute percentage error (MAPE) associated with these two algorithms also unambiguously outperform those of SVM. However, our study has found that SVM is still a useful algorithm in data fitting because it can produce reasonably accurate predictions within a tight time constraint. Our conclusion is that machine learning offers a promising, alternative technique in property valuation and appraisal research especially in relation to property price prediction.-
dc.languageeng-
dc.publisherRoutledge. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/09599916.asp-
dc.relation.ispartofJournal of Property Research-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectMachine Learning algorithms-
dc.subjectSVM-
dc.subjectRF-
dc.subjectGBM-
dc.subjectproperty valuation-
dc.titlePredicting property prices with machine learning algorithms-
dc.typeArticle-
dc.identifier.emailHo, WKO: winkyh@HKUCC-COM.hku.hk-
dc.identifier.emailTang, BS: bsbstang@hku.hk-
dc.identifier.authorityTang, BS=rp01646-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1080/09599916.2020.1832558-
dc.identifier.scopuseid_2-s2.0-85092761693-
dc.identifier.hkuros318767-
dc.identifier.volume38-
dc.identifier.issue1-
dc.identifier.spage48-
dc.identifier.epage70-
dc.identifier.isiWOS:000586644700001-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats