A Method of Semi-supervised Clustering for Group Decision-Making

It is a far more time-consuming and expensive task when the number of policy objectives and options is increasing for group decision-making. Based on the semi-supervised clustering, this paper proposes a novel approach to group decision-making. First, the semi-supervised clustering with partially labeled data is introduced as the means of making group decision. Second, the procedure of group decision-making is put forward to identify the optimum scheme and gain the extent of the desired objectives. Finally, a concrete case study is given to indicate the validity and feasibility of this new method.