Continually evolving customer’s needs has contributed to an increase in demand for product variety over the recent decades. Proliferation of product variants affects different aspects of product life cycle which increases the complexity of managing product variety. In this context, the notion of grouping and classification based on similarity within a family of product is the key in managing product variety. This research proposes hierarchical clustering as solution approach that is intuitively relevant and it focuses on progressively grouping the elements that share high similarity with each other. In this research, three types of product variety-related problems are investigated. The first problem concerns with designing product architecture in a way to support product variety. Design Structure Matrix (DSM) is used to visualize product architecture and to develop a new matrix-based clustering approach based on hierarchical cluster analysis. The challenge is that there are numerous possible product architectures even for a product with few components. One unique advantage of the proposed method lies in supporting ?overlapping components? which is not directly addressed by the conventional techniques in cluster analysis. The second problem focuses on structuring supply chain network in case of product variety that indicates the precedence orders of suppliers and sub-assemblers. The challenge is that the number of possible structures of supply chain network grows dramatically with the increase in the number of product variants. The solution approach is based on hierarchical clustering, in which the tree structure is applied to construct the supply chain network. The core technique is to investigate the coupling values between the module variants and characterizing the grouping condition in the structuring process. The third problem is to develop semi-finished products to reduce production costs. The challenge is that the possible solution space can increase exponentially with increase in the number of elements (e.g. components) in the problems. In the solution approach, the basic information of product variety is captured in a matrix format, specifying the component requirements for each product variant. Then, hierarchical clustering is applied over the components with the consideration of demands. The key stage is similarity analysis, in which problem-specific information can be incorporated in the clustering process. In summary, the proposed method can be a practical tool for tackling product variety-related problems. It yields good quality results in a limited time. Thus, it can be used to obtain better results than other algorithms when the amount of time available to perform the task is limited.