Home // WEB 2025, The Thirteenth International Conference on Building and Exploring Web Based Environments // View article

A Web Service Tool for Real Estate Price Estimation Powered by Machine Learning

Authors:
Abdul-Rahman Mawlood-Yunis
Youssef Roman

Keywords: Machine learning; Web services; Feature engineering; Real estate; House price estimation

Abstract:
Accurate estimation of housing prices is critical for informed decision-making in the real estate industry. This study develops a web-based platform that integrates machine learning (ML) algorithms to predict housing prices. Using a data set of more than 7,000 detached home transactions in Ontario's Halton region (2022-2023), the system applies advanced ML techniques and feature engineering, incorporating economic indicators like prime rates to enhance prediction accuracy. The platform combines ML-generated insights with an interactive interface, enabling real-time exploration of data, visualization of transaction patterns, and analysis of market shifts influenced by interest rate fluctuations. ML models such as Linear Regression, Random Forest, and XGBoost achieved high predictive performance, with R-squared values ranging from 0.93 to 0.997. Random Forest and Decision Tree models demonstrated the best capability in capturing price variability. These models are deployed through a user-friendly web application built with Flask, allowing users to predict home prices based on property features across multiple regions in the Greater Toronto Area (GTA). By leveraging ML, the tool enhances transparency and efficiency in the real estate market, offering homebuyers, sellers, and investors a reliable and accessible solution for real-time price estimation.

Pages: 20 to 26

Copyright: Copyright (c) IARIA, 2025

Publication date: March 9, 2025

Published in: conference

ISSN: 2308-4421

ISBN: 978-1-68558-243-2

Location: Lisbon, Portugal

Dates: from March 9, 2025 to March 13, 2025