Abstract

This study explores the application of machine learning models to predict rental prices in the dynamic real estate market of Dubai. With increasing demand for data-driven valuation tools, accurate rental price estimation has become essential for tenants, landlords, investors, and property consultants. The research is grounded in the theory of supervised machine learning, focusing on the use of structured property features—such as location, size, furnishing status, and number of rooms—to forecast monthly rent values. The study employed the “Dubai Real Estate Goldmine, UAE Rental Market Data” from Kaggle as its primary dataset. This data, which reflects thousands of residential listings across the UAE, was extensively preprocessed and analyzed to extract relevant features and identify trends. The research question aimed to determine which machine learning model could most effectively predict rental prices based on available structured data. Five regression models were trained and evaluated: Linear Regression, Ridge Regression, Support Vector Regressor (SVR), Random Forest Regressor, and XGBoost Regressor. Data was split into training and testing sets, and model performance was assessed using Mean Absolute Error (MAE) and R-squared (R²) metrics. Random Forest delivered the best results, with a MAE of AED 380 and an R² of 0.9998, indicating exceptional predictive accuracy. XGBoost also performed well, while SVR showed the weakest performance with a notably higher error margin and lower R² score. The findings confirm that ensemble models are better suited for capturing the complex, non-linear relationships present in real estate pricing. The project demonstrates that machine learning can be effectively used to build scalable, real-time pricing systems, provided appropriate models and features are selected. It also underscores the importance of data quality, feature engineering, and model tuning. Recommendations include the integration of temporal and geospatial features, deployment in interactive web applications, and exploration of deep learning approaches in future work. This research provides a strong foundation for building intelligent rental estimation tools and contributes to the broader field of AI applications in real estate analytics.

Publication Date

8-2026

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Ayman Ibrahim

Campus

RIT Dubai

Download

Share

COinS