Demand forecast by neuro-fuzzy techniques

This work presents the project for the development of an expert system for “demand forecast by neuro-fuzzy techniques”. The aim of the work is to study the feasibility of using fuzzy neural networks and compare the results to the ones obtained from conventional tools. For this purpose the work is focused on the development and representation of linguistic variables to qualify the product demand. The topics studied include: identification of linguistic variables in demand environment, and a comparative study of real data to the forecast results by means of an artificial neural network, a fuzzy neural network and FuturMaster (a tool based on Winters classic forecast method). The influence of the linguistic terms considered for the input/output variables is also analyzed