Clustering of multiple criteria alternatives for group selection with an application to machine-part cell formation

In many real world problems the range of consequences of different alternatives are considerably different. Also, sometimes, selection of a group of alternatives (instead of only one best alternative) is necessary. The traditional decision making approaches treat the set of alternatives with the same method of analysis and selection. We propose clustering alternatives into different sets so that different methods of analysis, selection and implementation for each group can be applied. As an example, consider the selection of a group of products for development by a corporation where there are many possible products to be developed. The group of products to be selected for development may vary in terms of their consequences and functions