Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic Data
In real estate appraisal, especially of residential buildings, one of the primary evaluation parameters is the property’s usable area. When determining the property price, Polish appraisers use data from comparable transactions included in the Real Estate Price Register (REPR), which is highly incom...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/3/863 |
_version_ | 1797623329536868352 |
---|---|
author | Leszek Dawid Kacper Cybiński Żanna Stręk |
author_facet | Leszek Dawid Kacper Cybiński Żanna Stręk |
author_sort | Leszek Dawid |
collection | DOAJ |
description | In real estate appraisal, especially of residential buildings, one of the primary evaluation parameters is the property’s usable area. When determining the property price, Polish appraisers use data from comparable transactions included in the Real Estate Price Register (REPR), which is highly incomplete, especially regarding properties’ usable areas. This incompleteness renders the identification of comparable transactions challenging and may lead to incorrect prediction of the property price. We address this challenge by applying machine learning methods to estimate the usable area of buildings with gable roofs based only on their topographic data, which is widely available in Poland in the Database of Topographic Objects (BDOT10k) of Light Detection and Ranging (LiDAR) origin. We show that three features are enough to make accurate predictions of the usable area: the covered area, the building’s height, and the number of stories optionally. A neural network trained on buildings from architectural bureaus reached a 4% median percentage error on the same source and 15% on the real buildings from the city of Koszalin, Poland. Therefore, the proposed method can be applied by appraisers to estimate the usable area of buildings with known transaction prices and solve the problem of finding comparable properties for appraisal. |
first_indexed | 2024-03-11T09:27:13Z |
format | Article |
id | doaj.art-67b30549f1734a84b9c65bf27df3f899 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-11T09:27:13Z |
publishDate | 2023-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-67b30549f1734a84b9c65bf27df3f8992023-11-16T17:55:19ZengMDPI AGRemote Sensing2072-42922023-02-0115386310.3390/rs15030863Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic DataLeszek Dawid0Kacper Cybiński1Żanna Stręk2Faculty of Civil Engineering, Environmental and Geodetic Sciences, Technical University of Koszalin, Śniadeckich 2, 75-453 Koszalin, PolandFaculty of Physics, University of Warsaw, Pasteura 5, 02-093 Warsaw, PolandDepartment of Environmental Engineering and Geodesy, The Faculty of Production Engineering, University of Life Sciences in Lublin, Akademicka 13, 20-950 Lublin, PolandIn real estate appraisal, especially of residential buildings, one of the primary evaluation parameters is the property’s usable area. When determining the property price, Polish appraisers use data from comparable transactions included in the Real Estate Price Register (REPR), which is highly incomplete, especially regarding properties’ usable areas. This incompleteness renders the identification of comparable transactions challenging and may lead to incorrect prediction of the property price. We address this challenge by applying machine learning methods to estimate the usable area of buildings with gable roofs based only on their topographic data, which is widely available in Poland in the Database of Topographic Objects (BDOT10k) of Light Detection and Ranging (LiDAR) origin. We show that three features are enough to make accurate predictions of the usable area: the covered area, the building’s height, and the number of stories optionally. A neural network trained on buildings from architectural bureaus reached a 4% median percentage error on the same source and 15% on the real buildings from the city of Koszalin, Poland. Therefore, the proposed method can be applied by appraisers to estimate the usable area of buildings with known transaction prices and solve the problem of finding comparable properties for appraisal.https://www.mdpi.com/2072-4292/15/3/863real estate appraisalneural networksurban remote sensingGIScienceLiDARlinear regression |
spellingShingle | Leszek Dawid Kacper Cybiński Żanna Stręk Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic Data Remote Sensing real estate appraisal neural networks urban remote sensing GIScience LiDAR linear regression |
title | Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic Data |
title_full | Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic Data |
title_fullStr | Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic Data |
title_full_unstemmed | Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic Data |
title_short | Machine Learning of Usable Area of Gable-Roof Residential Buildings Based on Topographic Data |
title_sort | machine learning of usable area of gable roof residential buildings based on topographic data |
topic | real estate appraisal neural networks urban remote sensing GIScience LiDAR linear regression |
url | https://www.mdpi.com/2072-4292/15/3/863 |
work_keys_str_mv | AT leszekdawid machinelearningofusableareaofgableroofresidentialbuildingsbasedontopographicdata AT kacpercybinski machinelearningofusableareaofgableroofresidentialbuildingsbasedontopographicdata AT zannastrek machinelearningofusableareaofgableroofresidentialbuildingsbasedontopographicdata |