In search of best alternatives: a TOPSIS driven MCDM procedure for neural network modeling

Multiple criteria decision making (MCDM) is an approach to rank the alternatives with respect to the different attributes. Several MCDM approaches were used to select the best alternatives of meta-heuristic modeling under the soft-computing domain where the true best alternative is not known. Alternatives are artificial neural network models, selection of which is difficult based on many conflicting performance measures. This paper addresses two new methods for MCDM, using the concept of Minkowski distance and based on technique for order preference by similarity to ideal solution philosophy. The performances of these two methods are compared with four other methods considering real-life data and simulated experiments.