In this thesis, we consider the effectiveness of Differential Evolution as a computational algorithm in the context of spare part inventory optimisation in a two-echelon supply chain setting. The study of DE in application to supply chain planning is limited; thus, we present a well-known hard discrete non-linear stochastic optimisation problem to determine the inventory investment for a two-echelon supply chain system. The underlying optimisation problem is notoriously difficult since it has discrete variables and is combinatorial in nature. We assume the best-in-class algorithm in the field of Operations Research to be the optimum optimisation algorithm for the problem under study. We aim to determine the accuracy of DE in generating to the best-in-class optimum solutions for the problem. We select DE control parameters that best fit the problem and select two DE Algorithm variants for the analysis. We create a series of complex conditions in which we expect DE to achieve the optimum solutions and present our case for comparison to the best-in-class method. We show specific enhancements to the DE algorithm to provide a robust method of achieving the optimum solutions unique to the problem under study. In addition, we derive conclusions on the scalability of DE and which DE algorithm is the preferred algorithm for the problem under study. Further, we formulate conclusions under which problem conditions; each DE Algorithm is best suited to achieve the optimum solutions and which DE Algorithm is comparable to the best-in-class analytical method. Finally, we present areas of further research for the application of DE in the context of inventory supply chain.