In this paper we provide a general process to create the most K-groups based on incomplete profiles and conditional preferences. The proposed approach is shown to be a combination of techniques that each output is the input of the next. It solves three problems: studying the incompletenesses of profiles based on conditional preferences, distances ans similarity measurement, and finding the top credible K-Groups of elements. Our process is efficient it's based on different previous works and tested techniques where each one returns a result that will be adjusted for the next step until the computation of the top K-Group is leaded. We provide a formal semantic of each step, and we describe how each technique provide an outcome that can be exploited according to the general process. Our work is customizable relevant to each approach and algorithm used. We ensure that the top K-Groups formation is reported with no loss in accuracy.