This work deals with the development of a predictive model for the anionic polymerization of lauryllactam activated by a particularly efficient catalytic system composed of aluminium hydride as catalyst and 4, 4 '-diphenylmethane diisocyanate urea as activator. This model takes into account important side reactions occurring during the process, i.e. branching reactions and Claisen's condensations giving rise to macromolecules with several functional end-groups. Its main key parameters are identified on the basis of batch experimental data which describe the complete sketch of polymerization. They allow to predict with a good precision the monomer conversion under different operating conditions. The model is then used to simulate the concentrations of the different functional end-groups as well as the number of condensation bonds per unit volume resulting from Claisen's condensations. (c) 2005 Elsevier Ltd. All rights reserved.