A method of optimising a sequential combinatorial process comprising an interchangeable sequence of events uses a master model to model a selection of the possible sequences. Information derived from the master model is used in a surrogate model that approximates the master model. The surrogate model calculates all possible sequences using an algorithm to select information calculated by the master model that most closely matches the events of a present sequence, following a prioritised system so that the best match is used wherever possible. All results from the surrogate model are compared to identify the modelled sequence that gives results closest to a desired optimum result.