The use of mass appraisal techniques is a common practice in real estate taxation. The models of real estate market have several sources of imprecision, such as errors in the transitions between submarkets, generating difficulties to construct mass appraisal models. Fuzzy Rule-Based Systems (FRBS) are able to generate flexible systems and may be useful in considering vagueness or imprecision presents in real estate market. This paper verifies the extraction of fuzzy rules from real estate data through genetic algorithms, performing Genetic Fuzzy Rule-Based Systems (GFRBS). These GFRBS used TSK rules, which are formed by linear equations and may be seen as hedonic models. Two approaches were tested. The first one is a GFRBS based on the gross building area of the properties, tested in systems with 3 to 7 rules. In another view, a system of rules based on location of the properties was constructed, in which each rule is specialized in determined region, and contributes to a general estimate. The systems were implemented with data of the city of Porto Alegre (Brazil), comparing the fuzzy models with a traditional hedonic regression model. The results have indicated the potential of fuzzy rules in mass appraisal.