An assembly consists of two or more mating parts. The quality of any assembly depends on quality of its mating parts. The mating parts may be manufactured using different machines and processes with different standard deviations. Therefore, the dimensional distributions of the mating parts are not similar. This results in clearance between the mating parts. All precision assemblies demand for a closer clearance variation. A significant amount of research has already been done to minimize clearance variation using selective assembly. Surplus part is one of the important issues, which reduces the implementation of selective assembly in real situation. Surplus parts are inevitable while the assembly is made from components with undesired dimensional distributions. Batch selective assembly is introduced in this paper to reduce surplus parts to zero and it is achieved by using nondominated sorting genetic algorithm-II. For demonstrating the proposed algorithm, a complex assembly which consists of piston, piston ring and cylinder is considered as an example problem. The proposed algorithm is tested with a set of experimental problem datasets and is found outperforming the other existing methods found in the literature, in producing solutions with minimum clearance variations with zero surplus parts. © 2011 Springer-Verlag London Limited.