An enhanced ordered weighted averaging operators generation algorithm with applications for multicriteria decision making

In the present paper, we demonstrate that the degree of orness, which measures the attitudes of decision-makers, does not decrease strictly with the fractile values when either the normal probability density function or its inverse form is used to generate the weights of ordered weighted averaging operators. As for the weights of ordered weighted averaging operators generated from either the exponential distribution and its inverse form, we prove the strict monotonicity of the orness function with respect to the distribution shape parameter. To solve the drawbacks of the probability-density-function-based weight generation approach, the present paper uses the interweaving method to adjust the probability-density-function-based weighting vector of an ordered weighted averaging operator based on the premise that the distribution shape parameter is excluded. This enhanced approach retains the preferences of decision-makers to the utmost when they change their attitudes toward objects. Finally, the feasibility and effectiveness of this novel paradigm for generating the weights of ordered weighted averaging operators are demonstrated with its promising application in a system for aggregating movie ratings.