Abstract A modeling of total evaluation process of sake ( Ginjo ) was studied using a fuzzy neural network(FNN). Total evaluation of 61 Ginjo samples was estimated from each data set of 7 sensory evaluations. In FNN model with all 7 input variables, the value of performance index, J TS , based on the errors between actual and estimated values was 0.025 and it was almost similar to that of NN model as reported previously. The FNN model obtained by Parameter Increasing Methods (PIM) was constructed with 2 membership functions for color, 3 for flavor top, 2 for flavor base and 3 for hard-soft, and J TS value of 0.013 was fairy small. The results suggest that the fuzzy modeling using a FNN is effective en the analysis of sensory evaluation process. In order to search the most optimum value of chemical components, both NN and genetic algorithm were also used.