PurposeAdvanced manufacturing machines (AMMs) are searched as a momentous asset across the manufacturing societies for quenching and addressing the production units under economical circumstances, i.e. production of high-quality of goods under feasible cost. AMMs are significant in holding the managers against their rivals and competitors with high profit margins. The authors developed the decision support mechanism/portfolio (DSM-P) consist of knowledge-based cluster approach with a dynamic model. The purpose of research work is to measure overall economic worth of AMMs under objective and grey-imperfect (mixed) data by exploring the proposed DSM-P.Design/methodology/approachThe authors developed the DSM-P that consist of knowledge-based cluster, three multi-criteria decision-making (MCDM) techniques-1-2-3 with complementary grey relational analysis-4(GRA), approach with a dynamic model (complied by technical plus cost and agility measures of AMMs). The proposed DSM-P enables the manager to map the overall economic worth of candidate AMMs under objective and grey-mixed data.FindingsThe presented DSM-P assist the managers for handling the selection problem of AMMs, i.e. CNCs, robots, automatic-guided vehicle, etc under mixed (objective cum grey) data. To enable the readers for intensely understand the work, the utility of proposed approach is displayed by illustrating a polar robot evaluation and selection problem. It is ascertained that the robot candidate-11 alternative is fulfilling the entire technical cum cost and agility measures.Originality/valueThe DSM-P provides more precise and reliable outcomes due to a usage of the dominance theory. Under the dominance theory, the ranks are obtained by MCDM techniques-1-2-3 are compared with ranks gathered by the GRA-4 under objective cum grey data, formed the novelties in presented research work. From a future perspective, the grey-based models in DSM-P can be built/extended/constructed more extensive and can be simulated by the same approach.