Summary: Artifician neural network and Fuzzy logic provide attractive ways to capture nonlinearities present in a complex system. Neuro-Fuzzy modelling, which is a newly emerging versatile area, is a judicious integration of merits of above mentioned two approaches. In this paper, an important model from this class, viz. Adaptive Neuro-Fuzzy Inference System (ANFIS) is thoroughly studied. The model is implemented on Fuzzy Logic Toolbox of MATLAB using ANFIS. As an illustration, the methodology is applied for development of a forecasting model for secondary data of yield of 100 banana plants on the basis of data at six different stages of growth using several biometrical characters like plant height, plant girth and leaf length as predictors.