Rental Property Demand and Supply Analysis Using Machine Learning

The real estate market in Dubai is famous for its activity and stimulating potential due to the geographical position of the emirate, well-developed transport and legal framework. Timely determination and prediction of rental price is crucial for investors, property owners and managers, tenants and authorities in their decision making to maximize returns and ensure market stability. Traditional approaches are insufficient for the analysis of the temporal and spatial relations between property characteristics and market processes, which require the use of sophisticated machine learning algorithms. This paper aims to predict the rental prices of properties in Dubai using machine learning models based on a dataset of 73023 property listings with noise, duplicate and outlier records removed. The dataset includes significant characteristics including property type, furnished or not, location, number of bedrooms and bathrooms, size of the property, payment frequency, age of listing, and usage. These features lay the basis for constructing more durable and accurate prediction models. Data preparation included categorical data conversion into numerical and scaling of the data for algorithms that are sensitive to the scale of data. Feature engineering and selection were performed using enhanced approaches to guarantee the dataset complexity and model performance. Four machine learning algorithms were explored that are Random Forest Regressor, SVR, XGBoost Regressor, and KNN Regressor. The dataset was split into training and testing sets in an 80:20 ratio, effectiveness of the models was evaluated based on Mean Absolute Error (MAE), Mean Squared Error (MSE), and coefficient of determination (R²). By cross validation we found that XGBoost and Random Forest performed better than other models in terms of accuracy and reliability. A feature importance analysis was conducted and reaffirmed that property size, location, and the number of bedrooms is the main determinants of rental prices. These findings are in concordance with the market realities whereby characteristics such as size and location are determinants of value. The study offers practical implications that can help stakeholders improve property assessment and rental pricing.