Probabilistic decision methodology based on hybrid model of grey clustering and extended dominance-based rough set

In order to abstract minimal knowledge presentation from multiple criteria information table,a hybrid approach of grey fixed weight clustering and extended dominance-based rough set is proposed.The basic idea of the hybrid method is as follows.Firstly,a multi-criteria information table with different dimensional preferential attributes is transformed into multi-criteria decision table by grey fixed weight clustering approach,then probabilistic decisions are made by means of extended dominance-based rough set approach,and preferential probabilistic decision models are derived.The proposed method is applied to evaluation of regional key technology,and the preferential probabilistic decision rules extracted can provide decision makers with decision reference.