A Hybrid Fuzzy LMS Neural Network Model for Determining Weights of Criteria in MCDM

A hybrid fuzzy LMS neural network model, with fuzzy numbers as inputs, is set up to determine the weights of each criterion of alternatives. The model can determine the weights of each criterion automatically, according to the time-series data of market, so that they are more objectively and accurately distributed. The model also has a strong self-learning ability so that calculations are greatly reduced and simplified. Further, decision maker's specific preferences for uncertainty also are considered in the model. Hence, this method can give revised results while taking into decision maker's subjective intensions for uncertainty preference. A numerical example is given to illustrate the method.