Abstract

It has been observed that the fastness of digital real estate’s application has resulted in availability of large-scale property data which forms an opportunity to more precise and open property valuation practices. A lot of conventional real estate appraisal methodologies with much emphasis on manual evaluation and historical comparative value find it difficult to respond to the market dynamics or the dynamics that exist within the market at an alarming rate. This research will help mitigate these shortcomings by generating and testing machine learning regression models to determine the price of residential property at sale in Dubai by using real-life data via Bayut property platform. The research was based on a quantitative, data-driven research methodology that is based on a positivist philosophy and a deductive research approach. The data was widely pre-processed by cleaning the data, performing feature engineering, outlier management, and coding nominal variables. The exploratory data analysis was made to determine the main patterns and relations of the data and then four regression-based models were created and compared: Linear Regression, Random Forest, XGBoost, and a Neural Network Regressor. Mean Absolute Error, Root Mean Squared Error, and coefficient of determination were used as measures of model performance. The findings reveal that machine learning models that are done in ensembles perform much better than the traditional linear regression when it comes to predicting property prices. The most promising model was identified to be the random forest which performed best in predictive accuracy and generalization performance, secondly was XGBoost. The results validate the property features including bedrooms and bathrooms being decisive in establishing prices and the high-sophistication machine learning methods are more appropriate to reflect non-linear associations built in the Dubai real estate business. Altogether, the research indicates how important data-driven valuation models are in improving the accuracy in pricing, the level of transparency in the market, and stakeholder decision-making in real estates.

Publication Date

4-2026

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Ehsan Warriach

Comments

This thesis has been embargoed. The full-text will be available on or around 11/12/2027.

Campus

RIT Dubai

Download

Share

COinS