Abstract

The purpose of this study is to find out the impact of data mining in predicting prices and values of real estate units in the Dubai real estate market. This market has always been one of the biggest markets in the economy of any nation worldwide and has always been considered one of the biggest indicators on the health of any economy. After the devastating crash of the world economy in 2008, many real estate projects were halted and economies are still recovering from that incident. Real estate brokers and agents found it difficult to sell any property during that period, and they are still following the same valuation procedure that they have been using since. They mainly value the unit based on the cost of the unit, return on investment, price comparison to similar units and are focused on the current market condition. The problem with this valuation procedure is that it fails to take into account historical data, state of the unit, price fluctuation in the location and other valuable pieces of information. With that in mind, data mining could prove to be extremely helpful in determining proper prices and values for real estate units that would allow buyers, sellers, and real estate agents to make more informed decisions. In this project we will be analyzing the Real Estate Market in the Emirate of Dubai to produce a model that can be predict the prices and valuations of real estate units in the emirate. We will collect demographic and property data, which will then be cleaned and combined for further analysis. The sources for the demographic dataset is Dubai Statistics Center and Google, while the source for the property dataset is PropertyFinder.ae. In the analysis stage useful plots will be produced to help understand the data and the relationship between the attributes. After which, a gradient boosting regression model will be used, and the data will be split into 80% training and 20% testing. The model managed to achieve an accuracy of 90.6%, and in the end our findings were compiled and example use cases were presented.

Publication Date

12-2020

Document Type

Master's Project

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research (Dubai)

Advisor

Sanjay Modak

Advisor/Committee Member

Ehsan Warriach

Campus

RIT Dubai

Download

Share

COinS