Ranking Fuzzy Variables by Expected Value and Variance

Ranking fuzzy numbers and fuzzy variables plays an important role in decision-making, data analysis, artificial intelligence and socioeconomic systems. Various approaches have been developed for ranking fuzzy numbers. Each of these techniques has been shown to produce non-intuitive results in certain cases. This paper proposes a new approach for ranking of fuzzy variables based on their expected values and variances within the framework of credibility theory. Some comparative examples are used to illustrate the advantage of the proposed method.