Research on Factors Affecting Real Estate Values by Data Mining

Abstract

Construction sector has an important place in Turkey’s economy. Real estate sales for the sector are increasing in parallel. However, the purchase cost is also important for those who are willing to buy a real estate. In the acquisition of real estate, factors such as size, location and age of the house are taken into consideration. The aim of the article is to conduct research on factors affecting real estate values by data mining. In this study, the most important variables that determine the value of the real estate have been investigated by data mining methods. The research has been carried out in Karabük and the variables determined according to the opinions of real estate experts. As classification methods, CHAID and C&RT algorithms have been used. It has been evaluated that both algorithm estimation results can be used. Within the framework of the study, the variables that have the most impact on the unit price have been determined, such as the size of the real estate, the distance to the city centre, the popularity, and the age of the building. The use of advanced technologies, such as statistical modelling and machine learning in real estate valuation and automatic value estimation, is of importance in determining the real value of the real estate.

Keywords

• chaid
• classification
• construction sector
• data mining
• decision tree
• real estate valuation