Abstract

Dubai’s rapidly evolving real estate market attracts substantial global investment yet remains characterized by information asymmetry, pricing volatility, and fragmented data sources. This study examines how integrated data analytics and ensemble machine learning can be used not primarily for precise price prediction, but rather to identify and quantify the key behavioral and transactional drivers of residential property prices in Dubai. A unified dataset was constructed by integrating over 100,000 residential property transactions from the Dubai Land Department with macroeconomic indicators, web-scraped listing attributes, and sentiment measures derived from online reviews and social media discussions. Supervised learning models including Linear Regression, Decision Trees, Random Forest, and Extreme Gradient Boosting (XGBoost) were developed and evaluated alongside clustering techniques such as K-Means and DBSCAN for market segmentation and behavioral profiling. While the overall predictive power of the models remained limited due to the highly volatile nature of the Dubai market (with the best model achieving an R² of 0.02), the models proved effective in revealing the relative importance of key price-forming factors. Crucially, the feature-importance analysis demonstrates that Investor Sentiment emerged as the second most influential driver of residential price formation, with an importance score of 27.3%, surpassing several traditional physical property attributes such as procedure area. Rather than positioning the models as precise forecasting tools, this research reframes their value as an analytical instrument for behavioral market interpretation and risk-aware decision support, and proposes an AI-enabled decision-support framework and interactive dashboards that translate analytical outputs into actionable insights for investors, developers, and policymakers, thereby enhancing market transparency and supporting more informed investment strategies within Dubai’s smart-city development agenda.

Library of Congress Subject Headings

Real property--Prices--United Arab Emirates--Dubai--Forecasting; Real property--Prices--United Arab Emirates--Dubai--Data processing; Machine learning

Publication Date

12-2025

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Sanjay Modak

Advisor/Committee Member

Ayman Ibrahim

Campus

RIT Dubai

Plan Codes

PROFST-MS

Download

Share

COinS