Multicomponent alloy (MCA) – a type of alloy that contains many components in equal or near-equal proportions with wide solubility ranges, exhibits a wide range and, in many cases, manifests superior mechanical properties compared to conventional alloy. However, due to the vast combinations of the number and composition of elements involved in the alloy, screening the composition-properties map for the entire multidimensional composition space using the conventional synthesize-test route in a short time is deemed infeasible. On the other hand, machine learning has been used for high-throughput screening in various engineering fields and potentially augments screening the composition-properties in MCAs. This study, therefore, proposes a hybrid scheme of heuristic algorithms and artificial neural network to predict the mechanical properties of a large compositional space combination in MCAs. The outcome of this study will aid material engineers in designing alloys tailored to specific properties and applications.