An MCDM approach to group processes using Choquet integration

We consider a model of non-additive Choquet aggregation in group processes, with reference to the context of effort estimation in Project Management. The groups considered are formed by “experts” (people with specific technical competence) and “non-experts” (people with less specific technical competence, usually experts in related fields), so that the typically complementary biases of the two classes contribute to a more balanced estimate. We present two simple examples which illustrate how the Choquet aggregation results improve those of the classical weighted mean (additive case). Finally, we discuss the relation between the average Choquet weights of consensual coalitions of experts and nonexperts and their individual Shapley values.