This paper introduces genetic algorithm (GA) based method to construct a satisfactory fuzzy system directly from some gathered input-output data of the discussed problem. In this method, each individual in the population is constructed to determine the number of fuzzy rules and the premise and the consequent part of the fuzzy system. With the special mutation operation and the adequate fitness function, the proposed method with GA produces a fuzzy system with small number of rules, suitable placement of the premise's fuzzy sets and proper location of the consequent singletons. Finally, example are illustrated to show the effectiveness of the proposed method.