Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP

This study proposes a weighted average ensemble model to predict the Officially Assessed Land Price in Sejong City, South Korea, using 500m <inline-formula> <tex-math notation="LaTeX">$\times 500$ </tex-math></inline-formula>m grid-based spatial data. The model anal...

Full description

Saved in:
Bibliographic Details
Main Authors: Surin Im, Kangmin Kim, Geunhee Lee, Hoi-Jeong Lim
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11017662/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138796178276352
author Surin Im
Kangmin Kim
Geunhee Lee
Hoi-Jeong Lim
author_facet Surin Im
Kangmin Kim
Geunhee Lee
Hoi-Jeong Lim
author_sort Surin Im
collection DOAJ
description This study proposes a weighted average ensemble model to predict the Officially Assessed Land Price in Sejong City, South Korea, using 500m <inline-formula> <tex-math notation="LaTeX">$\times 500$ </tex-math></inline-formula>m grid-based spatial data. The model analyzes the impact of key variables through SHAP for improved interpretability. Independent variables were grouped into three categories: building characteristics, population demographics, and accessibility to social infrastructure. To construct the predictive model, three boosting algorithms&#x2014;Gradient Boosting Machine (GBM), eXtreme Gradient Boosting (XGBoost), and LightGBM&#x2014;were evaluated. The optimal ensemble model, weighted as GBM:XGBoost:LightGBM =0:9:1, achieved a high predictive performance with R2 of 0.8964. SHAP analysis revealed five major factors influencing land price: floor area ratio, accessibility to fire stations, total male population, number of reinforced concrete buildings, and accessibility to general hospitals. The model&#x2019;s outputs were visualized through a grid-based land price map, revealing elevated land values within Sejong&#x2019;s Multifunctional Administrative City and around key transportation hubs. By employing fine-scale spatial data and enhancing model interpretability through SHAP, this research presents a robust empirical framework that addresses the limitations of traditional administrative-bound analyses. The findings provide valuable insights for data-driven policy formulation and the evaluation of the real estate market.
format Article
id doaj-art-2d1ba479b33c4f4ba8ead92a1985c0b7
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-2d1ba479b33c4f4ba8ead92a1985c0b72025-08-20T02:30:30ZengIEEEIEEE Access2169-35362025-01-0113962519626010.1109/ACCESS.2025.357469811017662Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAPSurin Im0https://orcid.org/0009-0009-9319-3764Kangmin Kim1https://orcid.org/0000-0002-8504-8622Geunhee Lee2https://orcid.org/0009-0007-2673-8352Hoi-Jeong Lim3https://orcid.org/0000-0002-0795-8305Graduate School of Data Science, Chonnam National University, Gwangju, Republic of KoreaGraduate School of Data Science, Chonnam National University, Gwangju, Republic of KoreaGraduate School of Data Science, Chonnam National University, Gwangju, Republic of KoreaGraduate School of Data Science, Chonnam National University, Gwangju, Republic of KoreaThis study proposes a weighted average ensemble model to predict the Officially Assessed Land Price in Sejong City, South Korea, using 500m <inline-formula> <tex-math notation="LaTeX">$\times 500$ </tex-math></inline-formula>m grid-based spatial data. The model analyzes the impact of key variables through SHAP for improved interpretability. Independent variables were grouped into three categories: building characteristics, population demographics, and accessibility to social infrastructure. To construct the predictive model, three boosting algorithms&#x2014;Gradient Boosting Machine (GBM), eXtreme Gradient Boosting (XGBoost), and LightGBM&#x2014;were evaluated. The optimal ensemble model, weighted as GBM:XGBoost:LightGBM =0:9:1, achieved a high predictive performance with R2 of 0.8964. SHAP analysis revealed five major factors influencing land price: floor area ratio, accessibility to fire stations, total male population, number of reinforced concrete buildings, and accessibility to general hospitals. The model&#x2019;s outputs were visualized through a grid-based land price map, revealing elevated land values within Sejong&#x2019;s Multifunctional Administrative City and around key transportation hubs. By employing fine-scale spatial data and enhancing model interpretability through SHAP, this research presents a robust empirical framework that addresses the limitations of traditional administrative-bound analyses. The findings provide valuable insights for data-driven policy formulation and the evaluation of the real estate market.https://ieeexplore.ieee.org/document/11017662/Grid datagradient boostingLightGBMXGBoostofficially assessed land priceSHAP
spellingShingle Surin Im
Kangmin Kim
Geunhee Lee
Hoi-Jeong Lim
Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP
IEEE Access
Grid data
gradient boosting
LightGBM
XGBoost
officially assessed land price
SHAP
title Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP
title_full Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP
title_fullStr Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP
title_full_unstemmed Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP
title_short Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP
title_sort development of a weighted average ensemble model for predicting officially assessed land prices using grid map data and shap
topic Grid data
gradient boosting
LightGBM
XGBoost
officially assessed land price
SHAP
url https://ieeexplore.ieee.org/document/11017662/
work_keys_str_mv AT surinim developmentofaweightedaverageensemblemodelforpredictingofficiallyassessedlandpricesusinggridmapdataandshap
AT kangminkim developmentofaweightedaverageensemblemodelforpredictingofficiallyassessedlandpricesusinggridmapdataandshap
AT geunheelee developmentofaweightedaverageensemblemodelforpredictingofficiallyassessedlandpricesusinggridmapdataandshap
AT hoijeonglim developmentofaweightedaverageensemblemodelforpredictingofficiallyassessedlandpricesusinggridmapdataandshap