Large-scale alternative processing group decision-making under Pythagorean linguistic preference environment

The traditional group decision-making (GDM) models do not intend to work with many alternatives. It is because experts like giving preference information based on a pairwise comparison of alternatives using preference relations. It is possible if the number of alternatives is small. If the number of alternatives is large, it is difficult for experts to give their preferred information. The current study mainly focuses on developing a new GDM model for managing many alternatives. In this model, experts like to create different groups of similar alternatives without getting lost among all available alternatives that have many alternatives without dealing with them directly. Then, we apply the hierarchical clustering method for clustering the alternatives. After that, one GDM model has spread to find the best cluster and select the final alternative using another. This paper uses Pythagorean linguistic preference relation (PLPR)-based GDM model in the two views. (1) Experts give their decision preferences comfortably instead of strict linguistic preference relations. (2) The PLPR-based GDM model is designed with consistency matrix-based group recommendations and feedback mechanism. The proposed GDM process is described with the example, which is the selection of companies of the fund manager in a mutual fund where the customers invest money for the best returns.