A FREQUENCY ANALYSIS APPROACH TO ENSURE THE ROBUSTNESS OF INTERACTIONS-BASED CLUSTERING OF PROJECT RISKS
Editor: Culley, S.J.; Hicks, B.J.; McAloone, T.C.; Howard, T.J. & Cantemessa, M.
Author: Marle, Franck; Vidal, Ludovic-Alexandre
Section: Design Organisation and Management
dent. An interactions-based clustering method which permitted to group risks, so that the interaction rate is maximal inside clusters and minimal outside, was presented with its associated tools and algorithms at ICED’09 conference with a case study in the entertainment industry. This article goes further into these approaches in order to obtain more robust results in order to facilitate the coordination of complex projects by reducing interfaces when dealing with risks. After some pages which introduce the problem and these approaches, we present an approach based on a frequency analysis, based on the variation of parameters of the quadratic integer clustering problem. A case study in the construction industry is finally presented (tramway design and construction project in a city). It permits to conclude on practical recommendations, conclusions and perspectives.