Housing price determinants in Istanbul, Turkey

Abstract

PurposeThe purpose of this paper is to analyze empirically major factors that affect housing prices in Istanbul, Turkey using the classification and regression tree (CART) approach.Design/methodology/approachThe data set was collected from various internet pages of real estate agencies during June 2007. The CART approach was then applied to derive main results and to make implications with regard to the housing market in Istanbul, Turkey.FindingsThe CART results indicate that sizes, elavators, existance of security, existance of central heating units and existance of view are the most important variables crucially affecting housing prices in Istanbul. The average price of houses in Istanbul was found to be 373,372.36 New Turkish Liras. The average size of a house was 138.37 m2. The average age of houses is 15.07 years old with the average number of rooms being 3.11. The average number of baths is 1.43 and average number of toilets is 1.22. Only 5 percent of homes have storage space, 45 percent of homes have parking space, 64 percent of homes are heated with furnace, whereas only 29 percent of homes are used central heating system. Among the 31 variables employed in this study, it was concluded size, elavator, security, central heating unit and view are the most important factors that have impact on housing prices in housing market in Istanbul.Practical implicationsFuture research and analysis of housing market in Istanbul and in Turkey can benefit from the method used in this study and findings derived from this research to come up with more general model(s) to include more houses in a wide range of regions in Turkey to analyze the determinants of housing prices in Turkey in general.Originality/valueExamining housing prices using the CART model is relatively new in the field of housing economics. Additionally, this study is the first to use the CART model to analyze housing market in Istanbul and in Turkey and derive valuable housing policies to be used by the authorities.

A Fully Automated Adjustment of Ensemble Methods in Machine Learning for Modeling Complex Real Estate Systems

“…is application is developed for the Singapore resale public housing market. However, although the process used to identify the main variables that affect the price of housing is extensive, its estimation is based solely on the average value in a leaf node of the tree, this value being thought of as a forecasting value or regression value.Özsoy and Şahin [23] develop a CART application in Turkey to determine the most influential characteristics on the price of housing in Istanbul based on a database taken from the Internet in 2007. e results lead them to conclude that the size of the house and the existence of an elevator, security, central heating, and views are the most influential variables on house prices in Istanbul.…”

“…ese same aspects are highlighted in [55,56] in which the authors point out that web prices offer a valuable opportunity for statistical analysis due to the constant generation of information, their accessibility, and availability as well as there being little notable differences compared to offline prices. Within real estate, applications developed using web data are used byÖzsoy and Şahin [23] in Istanbul; Del Cacho [14] in Madrid; Larraz and Larraz and Población [57,58] in Spain; Pow et al [17] in Montreal; Larraz and Población [59] in Czech Republic; Nguyen [25] in the United States; Clark and Lomax [36] in England; Pérez-Rave et al [20] in Colombia; or Neloy et al [44] in Bangladesh.…”

“…ese machine learning methods have been applied to the estimation of real estate properties in very specific locations. Research has been carried out by Jaen [12] in Coral Gables (Florida, USA); Fan et al [13] in Singapore (Republic of Singapore);Özsoy and Şahin [23] in Istanbul (Turkey); Del Cacho [14] in Madrid (Spain); Pow et al [17] in Montreal (Canada); Ceh et al [24] in Ljubljana, (Slovenia); Nguyen [25] in 5 counties of USA; and Dimopoulos et al [26] in Nicosia (Cyprus). In contrast, Pérez-Rave et al [20] deal with the estimation of dwelling prices for a whole country, Colombia, using independent variables identifying the city in which each property is located, thus proposing a unique model for the entire country (with a sample of 61,826 properties).…”

Determinants of Housing Prices in an Oil Based Economy

“…The main conclusion is that houses are not overpriced in Sweden. Ozsoy and Sahin (2009) analyze the factors affecting housing prices in Istanbul, Turkey. They found that beside location/area, the most dominating factors in the determination of house prices are sizes, elevators, available security measures, existence of central heating units and view of the house.…”

Estimating the residence price by linear regression model and Geographical Information Systems (GIS

“…As a result of the study during which non-residential consumption and residence expense data were used, Piazzesi, Schneider and Tuzel (2007) created an equilibrium model to estimate the residence prices. Ozsoy and Sahin (2009) have used the classification and regression tree (CART) approach in order to examine the essential parameters that affect the residence prices in Istanbul. As a result of this study, the area, elevator, security, central heating system and facade parameters have been determined to be the most important criteria for the residence prices in Istanbul.…”