Housing price determinants in Istanbul, Turkey: An application of the classification and regression tree model

Purpose - The 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/approach - The 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. Findings - The CART results indicate that sizes, elavators, existence of security, existence of central heating units and existence 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% of homes have parking space, 64% of homes are heated with furnace, whereas only 29% 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 implications - Future 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/value - Examining 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.