WSEAS Transactions on Computers
Print ISSN: 1109-2750, E-ISSN: 2224-2872
Volume 23, 2024
Leveraging Data Mining, Machine Learning, and Web Scraping for Forecasting Rental Housing Prices in Tunisia
Authors: Ala Balti, Mohamed Najeh Lakhoua, Mounir Sayadi
Abstract: The Tunisian real estate market has experienced a notable 13.5% surge in prices since 2018, marking a substantial departure from the preceding five years, during which there was a 9% growth, as indicated by data from the National Institute of Statistics (INS). According to the 2020 Rental Barometer, the average monthly rent for unfurnished apartments stands at 1,360 Tunisian dinars. Our initiative, titled "Predicting Real Rental Prices," employs advanced machine learning techniques to provide accurate predictions for rental prices. Users of this platform can plan moves, organize properties into categories, and customize rental price insights based on their preferences. This project is based on machine learning and uses deep learning algorithms to predict rental prices, thereby meeting the needs of both lessors and tenants. The model ensures a thorough and accurate forecasting approach by accounting for a number of issues, such as the effect of furniture and building conditions on rental prices.
Search Articles
Keywords: Prediction, Deep Learning, Machine Learning, Data Analyse, Correlation, Linear Regression, Random-Forest
Pages: 187-193
DOI: 10.37394/23205.2024.23.17
WSEAS Transactions on Computers, ISSN / E-ISSN: 1109-2750 / 2224-2872, Volume 23, 2024, Art. #17