Using Fuzzy Wavelet Neural Network to Solve MCDM Problem

Many practical problems are characterized as decision making with multiple, conflicting and noncommensurable nonlinear objectives and complex criteria. Especially in the practice of purchasing decision making, many quantitative and qualitative factors must be considered, as well as the vagueness and imprecision among them, which makes the decision process more complicated and unstructured. For identifying these nonlinear function structure and multiple attributes is a very difficult, time consuming, and confusing job in multiple criteria decision making (MCDM). This paper uses fuzzy wavelet neural network to improve the method of multiple criteria decision making, the model has the ability of self-study. We use the AHP method to determinate the initial weight, therefore making the trained weight more objective and exact. Moreover, By comparison of WNN and other methods, the result of WNN is basically consistent with other methods. This numerical example illustrated the correctness of our method.