Improving organization design by clustering project actors

This paper proposes to cluster project actors (i.e., members) to form complementary teams based on their interactions and interdependencies with each other. First, the Design Structure Matrix (DSM) is used to model the interactions between project members, which are based on the number of deliverables exchanged between them. Then, an agglomerative clustering technique is proposed to place the project members into groups. The algorithm permits management to impose certain restrictions on team formations, such as the number and maximum size of the teams, which members must be placed together, and which members must be kept apart. Most importantly, the algorithm allows cyclic information exchanges (i.e., loops) to be inserted into team clusters. It produces as output the recommended team formations, as well as the percentage of the total number of interactions that occur within the clustered teams. The proposed clustering method is illustrated using data collected from a vehicle development project at a large European automotive company.