Real Estate Valuation Using Artificial Neural Networks Method
Şükran Yalpır Osman Orhan Hari̇ka Ülkü Gamze Sarkım Güneri Ervural
AbstractThe real estate has an important position economically in the world. Proper valuation of the real estate is important for the country's economy. For the real estate valuation, it is necessary to know well the concept of value related to real estates and the factors, which affect the real estate value around the area. With the development of computer technology, it is possible to reach quick and accurate results by making detailed analyzes. In recent years, developments in artificial intelligence technologies have made artificial intelligence methods more attractive in real estate valuation. Also, advanced geographical information system (GIS) technology has started to use extensively in the real estate valuation. Thus, the creation of the databases, which has predominantly spatial information, for real estates increased the role of GIS in real estate valuation methods. In this study, positional analysis of agricultural data in the GIS environment was conducted and the factors affecting depreciation were examined. Artificial neural networks model is developed by data that are prepared in GIS environment. Subsequently, the success of the predicted outcome was assessed. As a result of this work is aimed to obtain accurate information about the value of agricultural land using mathematical modeling. The results show that real estate prediction study using ANN was in good agreement with absolute success value of 93% and correlation coefficient (R2) value of %76.