Multiple regression with fuzzy data
Fuzzy Sets and Systems
ANN+GIS: An automated system for property valuation
Neurocomputing
Expert Systems with Applications: An International Journal
The mass appraisal of the real estate by computational intelligence
Applied Soft Computing
Mathematical and Computer Modelling: An International Journal
Hi-index | 0.00 |
In this study, the effects of attribute reducing on real-estate valuation were investigated. Correlation was used for attribute reducing. To test the success of method, real-estate data which were collected from Konya region were used. The database consists of 190 data. 130 of them were used for training and 60 of them were used for testing. At the beginning, the number of attributes was 14. After attribute reducing, the number of attributes was reduced to 9. With these attributes, a new model was created. As a result of statistical calculations, it was found that the prediction success of method which is created with reduced attributes is higher than the prediction success of method which is created with all attributes.