Automatic clustering of business processes in business systems planning

In this paper, we apply the technique of hierarchical clustering to business processes identified in business systems planning which is an important methodology in information systems planning. A measure based on notions of cohesion and coupling is proposed as a guidance in searching for optimal number of clusters of business processes. By optimality, we mean that the net cohesion is maximized and net coupling is minimized. Moreover, we show that optimal number of clusters occurs at level of 0.5 in the hierarchy of partitions.