Generalised grey target decision method for mixed attributes based on the improved Gini-Simpson index

A new generalised grey target decision method for mixed attributes is presented. The proposed method makes a modification to the Gini-Simpson (G-S) index and adopts it as the basis of decision making. The improved version of G-S index could represent the difference (gap) between an alternative and its target centre as a whole and reflect the difference in various alternative indices and the similarity between alternative indices and target centre indices in detail. And the G-S index also has the advantage of combining the alternative index and target centre index in a simple and effective form. Besides, ranking alternatives easily or not by a given decision-making method is investigated, which arrives at the discrimination ability index. In decision making, the proposed method first transforms all mixed attribute indices into binary connection numbers and divides them into the deterministic terms and uncertain terms to constitute two-tuple (determinacy, uncertainty) numbers. Then the target centre indices of two-tuple (determinacy, uncertainty) number are determined. Following this, the improved comprehensive weighted Gini-Simpson index (CWGSI) of all alternatives can be obtained. Finally, the alternatives can be sorted with the CWGSI: the smaller the better. A case study exemplifies the proposed approach.