A New Data Normalization Method for Multi-criteria Decision Analysis

Due to the incommensurability between the criteria in the multiple criteria decision-making problem, we need to standardize the scores of alternatives against each criterion. Although the existing normalization method can transform the criterion scores into (0, 1), the averages of the criterion scores of all the alternatives for different criteria may be different. This is equivalent to the case that the criteria weights are revised. In order to solve this problem, a non-linear data normalization method is proposed in this paper. The proposed method can transform each criterion scores into (0, 1) and make the scores for each criterion have the same mean. Two examples are included to illustrate the rationality of the proposed approach.