Software product line (SPL) represents methods, tools, and techniques for creating a group of related software systems. Each product is a combination of multiple features. So, the task of production can be mapped to a feature subset selection problem, which is an NP-hard problem. This issue is very significant when the number of features in a software product line is huge. This chapter is aimed to address the feature subset selection in software product lines. Furthermore, the authors aim at studying the performance of a proposed multi-objective method in solving this NP-hard problem. Here, a multi-objective method (MOBAFS) is presented for feature selection in SPLs. The MOBAFS is a an optimization algorithm, which is inspired by the foraging behavior of honeybees. This technique is evaluated on five large-scale real-world software product lines in the range of 1,244 to 6,888 features. The proposed method is compared with the SATIBEA. According to the results of three solution quality indicators and two diversity metrics, the proposed method, in most cases, surpasses the other algorithm.