A desired prerequisite when performing a quantum mechanical calculation is to have an initial idea of the atomic positions within an approximate crystal structure. The atomic positions combined should result in a system located in, or close to, an energy minimum. However, designing low-energy structures may be challenging when prior knowledge is scarce, specifically for large multi-component systems where the degrees of freedom are close to infinite. In this paper we propose a method for identification of low-energy crystal structures in multi-component systems by combining cluster expansion and crystal structure prediction with density functional theory calculations. More importantly, we show that employing seed structures retrieved from cluster expansion models may significantly reduce the number of generations needed within the computationally demanding crystal structure prediction methodology. With this combined approach, we correctly identified the recently discovered Mo4/3Sc2/3AlB2 i-MAB phase comprised of in-plane chemical ordering of Mo and Sc and with Al in a Kagomé lattice. This result demonstrates that a combined approach provides a path for identifying low-energy crystal structures in multi-component systems by employing the strengths from both the cluster expansion method and the crystal structure prediction framework. In addition, we also address examples when cluster expansion fails to account for important structural transformations in sublattices not part of the parametrization.