Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of Çanakkale

Agricultural lands are known not only as agricultural production areas but also as areas with high income expectations as an investment tool. In Turkey, recent fluctuations in economic indicators such as the euro, dollar, and gold, along with increasing investment demand, have caused agricultural la...

Full description

Saved in:
Bibliographic Details
Main Authors: Simge Doğan, Levent Genç, Sait Can Yücebaş, Metin Uşaklı
Format: Article
Language:English
Published: Hasan Eleroğlu 2025-05-01
Series:Turkish Journal of Agriculture: Food Science and Technology
Online Access:https://agrifoodscience.com/index.php/TURJAF/article/view/7379
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850184142567768064
author Simge Doğan
Levent Genç
Sait Can Yücebaş
Metin Uşaklı
author_facet Simge Doğan
Levent Genç
Sait Can Yücebaş
Metin Uşaklı
author_sort Simge Doğan
collection DOAJ
description Agricultural lands are known not only as agricultural production areas but also as areas with high income expectations as an investment tool. In Turkey, recent fluctuations in economic indicators such as the euro, dollar, and gold, along with increasing investment demand, have caused agricultural land prices to rise uncontrollably. Controlling land price increases is important for preventing the misuse of agricultural lands. The sustainable management of agricultural lands and price stability are closely related to the United Nations Sustainable Development Goals (SDGs), particularly SDG 11 and 15, “Sustainable Cities and Communities” and “Life on Land.” In this context, accurately predicting prices is important for minimizing price fluctuations in agricultural lands for investors and landowners and supporting sustainable development. In general, the Multiple Linear Regression (MLR) model is considered one of the effective traditional methods for predicting real estate prices. However, depending on the data, more reliable results can be obtained than with powerful deep learning models such as the Extreme Gradient Boosting (XGBoost) algorithm, which exhibits superior prediction performance. This study aims to compare the MLR and XGBoost algorithms to predict agricultural land prices in villages located in the central district of Çanakkale and to examine daily fluctuations in economic indicators such as the dollar, gold, and euro. The results showed that XGBoost (R2 = 0.66) has an advantage in terms of coefficient of determination values compared to MLR (R2 = 0.01). Accurate price prediction for agricultural lands will help control fluctuations in land prices. Additionally, it will support farmers and investors in making informed decisions for a sustainable agricultural economy.
format Article
id doaj-art-90150831742b448b8229c1ef888244d4
institution OA Journals
issn 2148-127X
language English
publishDate 2025-05-01
publisher Hasan Eleroğlu
record_format Article
series Turkish Journal of Agriculture: Food Science and Technology
spelling doaj-art-90150831742b448b8229c1ef888244d42025-08-20T02:17:06ZengHasan EleroğluTurkish Journal of Agriculture: Food Science and Technology2148-127X2025-05-011351109111610.24925/turjaf.v13i5.1109-1116.73796080Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of ÇanakkaleSimge Doğan0https://orcid.org/0000-0001-5085-9540Levent Genç1https://orcid.org/0000-0002-0074-0987Sait Can Yücebaş2https://orcid.org/0000-0002-1030-3545Metin Uşaklı3https://orcid.org/0009-0009-8245-5976Çanakkale Onsekiz Mart University, School of Graduate Studies, Department of Real Estate Development, 17000, Çanakkale, TürkiyeÇanakkale Onsekiz Mart University, Faculty of Architecture and Design, Department of Urban and Regional Planning, Land Use and Climate Change Laboratory (LULC-Lab), 17000, Çanakkale, TürkiyeÇanakkale Onsekiz Mart University, Faculty of Engineering, Department of Computer Engineering, 17000, Çanakkale, TürkiyeComputer Agriculture Environmental Planning (ComAgEnPlan) Working Group, 17000, Çanakkale, TürkiyeAgricultural lands are known not only as agricultural production areas but also as areas with high income expectations as an investment tool. In Turkey, recent fluctuations in economic indicators such as the euro, dollar, and gold, along with increasing investment demand, have caused agricultural land prices to rise uncontrollably. Controlling land price increases is important for preventing the misuse of agricultural lands. The sustainable management of agricultural lands and price stability are closely related to the United Nations Sustainable Development Goals (SDGs), particularly SDG 11 and 15, “Sustainable Cities and Communities” and “Life on Land.” In this context, accurately predicting prices is important for minimizing price fluctuations in agricultural lands for investors and landowners and supporting sustainable development. In general, the Multiple Linear Regression (MLR) model is considered one of the effective traditional methods for predicting real estate prices. However, depending on the data, more reliable results can be obtained than with powerful deep learning models such as the Extreme Gradient Boosting (XGBoost) algorithm, which exhibits superior prediction performance. This study aims to compare the MLR and XGBoost algorithms to predict agricultural land prices in villages located in the central district of Çanakkale and to examine daily fluctuations in economic indicators such as the dollar, gold, and euro. The results showed that XGBoost (R2 = 0.66) has an advantage in terms of coefficient of determination values compared to MLR (R2 = 0.01). Accurate price prediction for agricultural lands will help control fluctuations in land prices. Additionally, it will support farmers and investors in making informed decisions for a sustainable agricultural economy.https://agrifoodscience.com/index.php/TURJAF/article/view/7379
spellingShingle Simge Doğan
Levent Genç
Sait Can Yücebaş
Metin Uşaklı
Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of Çanakkale
Turkish Journal of Agriculture: Food Science and Technology
title Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of Çanakkale
title_full Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of Çanakkale
title_fullStr Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of Çanakkale
title_full_unstemmed Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of Çanakkale
title_short Analyzing Agricultural Land Price Prediction Using Linear Regression and XGBoost Machine Learning Algorithms: A Case Study of Çanakkale
title_sort analyzing agricultural land price prediction using linear regression and xgboost machine learning algorithms a case study of canakkale
url https://agrifoodscience.com/index.php/TURJAF/article/view/7379
work_keys_str_mv AT simgedogan analyzingagriculturallandpricepredictionusinglinearregressionandxgboostmachinelearningalgorithmsacasestudyofcanakkale
AT leventgenc analyzingagriculturallandpricepredictionusinglinearregressionandxgboostmachinelearningalgorithmsacasestudyofcanakkale
AT saitcanyucebas analyzingagriculturallandpricepredictionusinglinearregressionandxgboostmachinelearningalgorithmsacasestudyofcanakkale
AT metinusaklı analyzingagriculturallandpricepredictionusinglinearregressionandxgboostmachinelearningalgorithmsacasestudyofcanakkale