Method For Determining Values In Real Estate Appraisal: comparing between Linear Regression Model and Fuzzy Logic

Fuzzy logic is a suitable tool for dealing with uncertain variables and it can contribute considerably with the techniques currently used in real state properties valuation, due to the fact that some variables, which define the value of a property, are difficult to be modeled, for instance the changes of buyers and sellers from a property to another one. Because it is a supervised approach technique was necessary in-depth knowledge of the area of interest, targeting the choice of variables and exploitation of data. In this context, the aim of this study was testing the use of fuzzy logic as an alternative for the assessment of real estate values, proposing a new method to model the real estate market. A sample of real data from the town Álvares Machado-SP was used in the experiments. The results obtained with fuzzy logic were compared with those obtained from a traditional method, which is usually performed using linear regression. The comparison between the methods showed that the best results were obtained with the regression model. However, the fuzzy logic model showed to have good potential for the real estate values assessment.

Keywords:
Real estate appraisal; Fuzzy Logic; Average Real Estate Price Map.