House Market Prediction Using Machine Learning

This study compares tree-based machine learning algorithms for predicting Bucharest residential apartment prices. Using a dataset from March 2025, comprehensive preprocessing—including imputation, categorical encoding, and feature engineering (e.g., distance to public transport)—was applied. Models...

Full description

Saved in:
Bibliographic Details
Main Author: Nicușor-Andrei ANDREI
Format: Article
Language:English
Published: Bucharest University of Economic Studies 2025-01-01
Series:Database Systems Journal
Subjects:
Online Access:https://www.dbjournal.ro/archive/36/36_6.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850114245738364928
author Nicușor-Andrei ANDREI
author_facet Nicușor-Andrei ANDREI
author_sort Nicușor-Andrei ANDREI
collection DOAJ
description This study compares tree-based machine learning algorithms for predicting Bucharest residential apartment prices. Using a dataset from March 2025, comprehensive preprocessing—including imputation, categorical encoding, and feature engineering (e.g., distance to public transport)—was applied. Models were optimized via grid search with 5-fold cross-validation and evaluated using RMSE, MAE, and R². Results show XGBoost outperforms Random Forest and Decision Tree models across all metrics.
format Article
id doaj-art-0fa20893a91f4c609a74e0bcafbdebad
institution OA Journals
issn 2069-3230
language English
publishDate 2025-01-01
publisher Bucharest University of Economic Studies
record_format Article
series Database Systems Journal
spelling doaj-art-0fa20893a91f4c609a74e0bcafbdebad2025-08-20T02:36:57ZengBucharest University of Economic StudiesDatabase Systems Journal2069-32302025-01-011615564RePEc:aes:dbjour:v:16:y:2025:i:1:p:55-64House Market Prediction Using Machine LearningNicușor-Andrei ANDREI0The Bucharest University of Economic Studies, RomaniaThis study compares tree-based machine learning algorithms for predicting Bucharest residential apartment prices. Using a dataset from March 2025, comprehensive preprocessing—including imputation, categorical encoding, and feature engineering (e.g., distance to public transport)—was applied. Models were optimized via grid search with 5-fold cross-validation and evaluated using RMSE, MAE, and R². Results show XGBoost outperforms Random Forest and Decision Tree models across all metrics.https://www.dbjournal.ro/archive/36/36_6.pdfhouse marketmachine learningprice predictiontree-based algorithmsxgboost
spellingShingle Nicușor-Andrei ANDREI
House Market Prediction Using Machine Learning
Database Systems Journal
house market
machine learning
price prediction
tree-based algorithms
xgboost
title House Market Prediction Using Machine Learning
title_full House Market Prediction Using Machine Learning
title_fullStr House Market Prediction Using Machine Learning
title_full_unstemmed House Market Prediction Using Machine Learning
title_short House Market Prediction Using Machine Learning
title_sort house market prediction using machine learning
topic house market
machine learning
price prediction
tree-based algorithms
xgboost
url https://www.dbjournal.ro/archive/36/36_6.pdf
work_keys_str_mv AT nicusorandreiandrei housemarketpredictionusingmachinelearning