Incorporating remote sensing information in modeling house values

A regression tree approach

Danlin Yu, Changshan Wu

Research output: Contribution to journalArticleResearchpeer-review

15 Citations (Scopus)

Abstract

This paper explores the possibility of incorporating remote sensing information in modeling house values in the City of Milwaukee, Wisconsin, U.S.A. In particular, a Landsat ETM+ image was utilized to derive environmental characteristics, including the fractions of vegetation, impervious surface, and soil, with a linear spectral mixture analysis approach. These environmental characteristics, together with house structural attributes, were integrated to house value models. Two modeling techniques, a global OLS regression and a regression tree approach, were employed to build the relationship between house values and house structural and environmental characteristics. Analysis of results indicates that environmental characteristics generated from remote sensing technologies have strong influences on house values, and the addition of them improves house value modeling performance significantly. Moreover, the regression tree model proves as a better alternative to the OLS regression models in terms of predicting accuracy. In particular, based on the testing dataset, the mean average error (MAE) and relative error (RE) dropped from 0.202 and 0.434 for the OLS model to 0.134 and 0.280 for the regression tree model, while the correlation coefficient between the predicted and observed values increased from 0.903 to 0.960. Further, as a nonparametric and local model, the regression tree method alleviates the problems with the OLS techniques and provides a means in delineating urban housing submarkets.

Original languageEnglish
Pages (from-to)129-138
Number of pages10
JournalPhotogrammetric Engineering and Remote Sensing
Volume72
Issue number2
DOIs
StatePublished - 1 Jan 2006

Fingerprint

Remote sensing
remote sensing
modeling
urban housing
Landsat
Soils
vegetation
Testing
soil
analysis

Cite this

@article{272a446fcf5242f1a990a6b80931fbd0,
title = "Incorporating remote sensing information in modeling house values: A regression tree approach",
abstract = "This paper explores the possibility of incorporating remote sensing information in modeling house values in the City of Milwaukee, Wisconsin, U.S.A. In particular, a Landsat ETM+ image was utilized to derive environmental characteristics, including the fractions of vegetation, impervious surface, and soil, with a linear spectral mixture analysis approach. These environmental characteristics, together with house structural attributes, were integrated to house value models. Two modeling techniques, a global OLS regression and a regression tree approach, were employed to build the relationship between house values and house structural and environmental characteristics. Analysis of results indicates that environmental characteristics generated from remote sensing technologies have strong influences on house values, and the addition of them improves house value modeling performance significantly. Moreover, the regression tree model proves as a better alternative to the OLS regression models in terms of predicting accuracy. In particular, based on the testing dataset, the mean average error (MAE) and relative error (RE) dropped from 0.202 and 0.434 for the OLS model to 0.134 and 0.280 for the regression tree model, while the correlation coefficient between the predicted and observed values increased from 0.903 to 0.960. Further, as a nonparametric and local model, the regression tree method alleviates the problems with the OLS techniques and provides a means in delineating urban housing submarkets.",
author = "Danlin Yu and Changshan Wu",
year = "2006",
month = "1",
day = "1",
doi = "10.14358/PERS.72.2.129",
language = "English",
volume = "72",
pages = "129--138",
journal = "Photogrammetric Engineering and Remote Sensing",
issn = "0099-1112",
publisher = "American Society for Photogrammetry and Remote Sensing",
number = "2",

}

Incorporating remote sensing information in modeling house values : A regression tree approach. / Yu, Danlin; Wu, Changshan.

In: Photogrammetric Engineering and Remote Sensing, Vol. 72, No. 2, 01.01.2006, p. 129-138.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Incorporating remote sensing information in modeling house values

T2 - A regression tree approach

AU - Yu, Danlin

AU - Wu, Changshan

PY - 2006/1/1

Y1 - 2006/1/1

N2 - This paper explores the possibility of incorporating remote sensing information in modeling house values in the City of Milwaukee, Wisconsin, U.S.A. In particular, a Landsat ETM+ image was utilized to derive environmental characteristics, including the fractions of vegetation, impervious surface, and soil, with a linear spectral mixture analysis approach. These environmental characteristics, together with house structural attributes, were integrated to house value models. Two modeling techniques, a global OLS regression and a regression tree approach, were employed to build the relationship between house values and house structural and environmental characteristics. Analysis of results indicates that environmental characteristics generated from remote sensing technologies have strong influences on house values, and the addition of them improves house value modeling performance significantly. Moreover, the regression tree model proves as a better alternative to the OLS regression models in terms of predicting accuracy. In particular, based on the testing dataset, the mean average error (MAE) and relative error (RE) dropped from 0.202 and 0.434 for the OLS model to 0.134 and 0.280 for the regression tree model, while the correlation coefficient between the predicted and observed values increased from 0.903 to 0.960. Further, as a nonparametric and local model, the regression tree method alleviates the problems with the OLS techniques and provides a means in delineating urban housing submarkets.

AB - This paper explores the possibility of incorporating remote sensing information in modeling house values in the City of Milwaukee, Wisconsin, U.S.A. In particular, a Landsat ETM+ image was utilized to derive environmental characteristics, including the fractions of vegetation, impervious surface, and soil, with a linear spectral mixture analysis approach. These environmental characteristics, together with house structural attributes, were integrated to house value models. Two modeling techniques, a global OLS regression and a regression tree approach, were employed to build the relationship between house values and house structural and environmental characteristics. Analysis of results indicates that environmental characteristics generated from remote sensing technologies have strong influences on house values, and the addition of them improves house value modeling performance significantly. Moreover, the regression tree model proves as a better alternative to the OLS regression models in terms of predicting accuracy. In particular, based on the testing dataset, the mean average error (MAE) and relative error (RE) dropped from 0.202 and 0.434 for the OLS model to 0.134 and 0.280 for the regression tree model, while the correlation coefficient between the predicted and observed values increased from 0.903 to 0.960. Further, as a nonparametric and local model, the regression tree method alleviates the problems with the OLS techniques and provides a means in delineating urban housing submarkets.

UR - http://www.scopus.com/inward/record.url?scp=33144480471&partnerID=8YFLogxK

U2 - 10.14358/PERS.72.2.129

DO - 10.14358/PERS.72.2.129

M3 - Article

VL - 72

SP - 129

EP - 138

JO - Photogrammetric Engineering and Remote Sensing

JF - Photogrammetric Engineering and Remote Sensing

SN - 0099-1112

IS - 2

ER -