The time series forecasting is present in several areas such as electrical, financial, economy and industry. In all these areas, the forecasts are critical to decision making in the short, medium and long term. Certainly, statistical techniques are most often used in time series forecasting problems, mainly because of a greater degree of interpretability, guaranteed by the mathematical models generated. However, computational intelligence techniques have been increasingly applied in time series forecasting in academic research, with emphasis on Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS). There are many cases of successful application of ANNs, but the systems developed are black box, not allowing a better understanding of the final prediction. On the other hand the FIS are interpretable, but its application is compromised by reliance on rule-making by experts and by the difficulty in adjusting the various parameters as the number and shape of fuzzy sets and the window size. Moreover, the lack of people with the knowledge necessary for the development and use of models based on these techniques also restricts their application in the routine planning and decision making in most organizations. This work aims to develop a computational tool able to make forecasts of time series, based on the theory of Fuzzy Inference Systems, in conjunction with the optimization of parameters by Genetic Algorithms, providing an intuitive and friendly graphical user interface.