In this paper, we deal with group multiattribute utility analysis incorporating preferences of multiple interested individuals.Since it is difficult to repeatedly ask them questions for determining parameters of a multiattribute utility function, we gather preference information of them by asking not difficult questions to answer, and develop a method for selecting an alternative consistent with the preference information. For a given set of single-attribute utility functions, assuming multiattribute utility functions to be in the multiplicative form, we evaluate trade-off between attributes by utilizing neural networks. Using the preference information actually gathered in an application study[12], we verify the effectiveness of the proposed method.