An improved approach to conjoint analysis for the complex decision-making

The classical conjoint analysis (CA) has three drawbacks in computing preference values of the evaluated objects. Firstly, the three estimation methods of profile utilities may be invalid. Secondly, the three methods do not well reflect inherent interactive relations of complex systems. Thirdly, CA does not consider inaccurate characteristic of evaluators' judgments. Therefore, conclusions made by the classical CA are probably incorrect. To overcome these three drawbacks, according to the thought of the meta-synthesis from qualitative analysis to quantitative analysis of complex system theory, and based on the theory of the technique of fuzzy neural network, the improved approach to CA for the complex decision-making is presented. The numerical demonstration verifies that the developed approach is able to obtain rank of evaluated objects much closer to the real, and proves to be more reasonable than the classical CA.