Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, Brazil

Mass appraisal has significant applications, such as urban planning, real estate appraisal, and property tax. Due to the challenges of analyzing massive models, they are often developed using semi-automatic assessment methods and machine learning techniques. This article explores different appraisal...

Full description

Saved in:
Bibliographic Details
Main Authors: Antônio Augusto Ferreira de Oliveira, Fabián Reyes-Bueno, Marco Aurelio Stumpf Gonzalez, Éverton da Silva
Format: Article
Language:English
Published: Firenze University Press 2025-02-01
Series:Aestimum
Subjects:
Online Access:https://oaj.fupress.net/index.php/ceset/article/view/15344
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849721427602702336
author Antônio Augusto Ferreira de Oliveira
Fabián Reyes-Bueno
Marco Aurelio Stumpf Gonzalez
Éverton da Silva
author_facet Antônio Augusto Ferreira de Oliveira
Fabián Reyes-Bueno
Marco Aurelio Stumpf Gonzalez
Éverton da Silva
author_sort Antônio Augusto Ferreira de Oliveira
collection DOAJ
description Mass appraisal has significant applications, such as urban planning, real estate appraisal, and property tax. Due to the challenges of analyzing massive models, they are often developed using semi-automatic assessment methods and machine learning techniques. This article explores different appraisal model methods that utilize statistics and machine learning. It also looks at incorporating spatial information to see if the chosen method can effectively capture the typical spatial dependency of the real estate market. This can help reduce the spatial autocorrelation observed in the residuals. The study compared nine machine learning methods with traditional statistical approaches using a dataset of over 43,000 apartments in Fortaleza, Brazil. The results of the machine learning algorithms were similar. The XGBoost minimized spatial autocorrelation. The easiest interpretations were with MRA, M5P, and MARS techniques. Although, these techniques had the greatest residual spatial autocorrelations. There is a trade-off between the methods, depending on whether the aim is to improve accuracy or provide a clear explanation for property taxation.
format Article
id doaj-art-14ac92bb3d1a4078b4dab6d7a3fc5211
institution DOAJ
issn 1592-6117
1724-2118
language English
publishDate 2025-02-01
publisher Firenze University Press
record_format Article
series Aestimum
spelling doaj-art-14ac92bb3d1a4078b4dab6d7a3fc52112025-08-20T03:11:39ZengFirenze University PressAestimum1592-61171724-21182025-02-018510.36253/aestim-15344Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, BrazilAntônio Augusto Ferreira de Oliveira0Fabián Reyes-Bueno1Marco Aurelio Stumpf Gonzalez2Éverton da Silva3Municipal treasury auditor of Fortaleza, BrazilFacultad de Ciencias Exactas y Naturales, Universidad Técnica Particular de Loja, Loja, EcuadorPolytechnic School, Universidade do Vale do Rio dos Sinos, São Leopoldo, BrazilGeosciences Department, Universidade Federal de Santa Catarina, Florianópolis, BrazilMass appraisal has significant applications, such as urban planning, real estate appraisal, and property tax. Due to the challenges of analyzing massive models, they are often developed using semi-automatic assessment methods and machine learning techniques. This article explores different appraisal model methods that utilize statistics and machine learning. It also looks at incorporating spatial information to see if the chosen method can effectively capture the typical spatial dependency of the real estate market. This can help reduce the spatial autocorrelation observed in the residuals. The study compared nine machine learning methods with traditional statistical approaches using a dataset of over 43,000 apartments in Fortaleza, Brazil. The results of the machine learning algorithms were similar. The XGBoost minimized spatial autocorrelation. The easiest interpretations were with MRA, M5P, and MARS techniques. Although, these techniques had the greatest residual spatial autocorrelations. There is a trade-off between the methods, depending on whether the aim is to improve accuracy or provide a clear explanation for property taxation. https://oaj.fupress.net/index.php/ceset/article/view/15344 semi-automatic assessment methodsmass appraisal techniquesmachine learning
spellingShingle Antônio Augusto Ferreira de Oliveira
Fabián Reyes-Bueno
Marco Aurelio Stumpf Gonzalez
Éverton da Silva
Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, Brazil
Aestimum
semi-automatic assessment methods
mass appraisal techniques
machine learning
title Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, Brazil
title_full Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, Brazil
title_fullStr Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, Brazil
title_full_unstemmed Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, Brazil
title_short Comparing traditional and machine learning techniques in apartments mass appraisal in Fortaleza, Brazil
title_sort comparing traditional and machine learning techniques in apartments mass appraisal in fortaleza brazil
topic semi-automatic assessment methods
mass appraisal techniques
machine learning
url https://oaj.fupress.net/index.php/ceset/article/view/15344
work_keys_str_mv AT antonioaugustoferreiradeoliveira comparingtraditionalandmachinelearningtechniquesinapartmentsmassappraisalinfortalezabrazil
AT fabianreyesbueno comparingtraditionalandmachinelearningtechniquesinapartmentsmassappraisalinfortalezabrazil
AT marcoaureliostumpfgonzalez comparingtraditionalandmachinelearningtechniquesinapartmentsmassappraisalinfortalezabrazil
AT evertondasilva comparingtraditionalandmachinelearningtechniquesinapartmentsmassappraisalinfortalezabrazil