A Comparison of Grading Models for Neighborhood Level of Family Housing Units
More recently Turkey has witnessed fast housing development and real estate sector growth because of the mortgage preparations. With this development, property location quality has been considered important for selecting and paying them. This study uses a data set of new single family housing units in Kocaeli University Campus Area. By using 4 location quality criteria, 27 single family housing units are graded at the neighborhood level. It is aimed to examine the applications of grading property at the neighborhood level based on property location quality by testing with three methods. Traditional method and fuzzy logic method were discussed in our antecedent studies. In this study, an easy used numerical calculation method; Neural Networks (NN), is introduced. Its grading performance is compared with the previous methods. NN method is found to be more accurate and realistic than traditional grading approach where its designing stage is more practical and faster than fuzzy logic approach.
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
When requesting a correction, please mention this item's handle: RePEc:wiw:wiwrsa:ersa11p966. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Gunther Maier)
If references are entirely missing, you can add them using this form.