Quantile-induced vector-based heavy OWA operator and the application in dynamic decision making

To the incentive problems in dynamic decision making, we propose a new type of aggregation operator denoted the quantile-induced vector-based heavy ordered weighted averaging (QI-VHOWA) operator. The main characteristic of the operator is that the arguments are aggregated using the form of vector. Additionally, the decision maker's incentive expectation is integrated into the aggregation process by various segmented incentive coefficients. We calculate the quantile measures of the argument vectors based on the technique for order of preference by similarity to ideal solution method. We determine the QI-VHOWA weighting vector by considering the location position of an alternative's performance as well as the development trend. The primary properties of the operator are discussed, including commutativity, boundness, and monotonicity under certain conditions. Finally, a numerical example regarding the evaluation of employees' performances in multiple periods is provided. The results are compared with that of the vector-based OWA and vector-based weighted arithmetic averaging operators. It is found that the incentive effectiveness of the QI-VHOWA is the most significant. The use of the QI-VHOWA operator is helpful to guide the long-term development of an alternative.