In this paper, we are interested in a family of multi- criteria ranking methods called Ranking with Multiple reference Points (RMP). This method is based on pairwise comparisons, but instead of directly comparing any pair of alternatives, it compares rather the alternatives to a set of predefined reference points. We actually focus on a Simplified RMP model (S-RMP) in which the preference parameters include the criteria weights and the set of ref- erence points ordered by importance. Elicitation of the parameters (from the data provided by the decision makers) leads us to the pref- erence learning algorithms that cannot only be applied on relatively small dataset. Therefore, we propose in this work a preference learn- ing methodology for learning S-RMP models from a large set of pair- wise comparisons of alternatives. The newly proposed algorithm is a combination of an Evolutionary Algorithm and a Linear Program- ming approach. Empirical results and analysis are also presented.