Application Artificial Neural Network in Mass Real Estate Appraisal for Centre Neighborhood of Konya
Fatma Bunyan Unel Şükran Yalpır
AbstractMass appraisal of real estate is a complex problem because of multiple criteria. Developed technologic methods provide a solution by transforming into the form of simple and easy. Multiple Regression Analysis (MRA) is frequently used in academic and practice studies in the world and our country. New method quest continues according to recent advances in computer technology. Artificial Neural Network (ANN) which is one of the artificial intelligence methods should investigate in order to use in the valuation because it can imitate human brain. The aim of this study is to estimate with ANN method the value of real estate. The study data consisted of the market samples concerning the plots in Centre Neighborhood of Konya. The data of the 558 samples were collected as main headings in the form of Legal, Physical, Locational and Neighborhood Features. The data set was separated for 70% training and 30% test. The market values of the plots were forecasted by using 70% training data with ANN and MRA methods and compared by testing 30% data in both methods. According to the results, it has seemed that success of ANN method is higher than the success of MRA method.