Exploring 2-rank strategic weight manipulation in multiple attribute decision making and its applications in project review and university ranking. (January 2023)

• Record Type: Journal Article
• Authors: Liu, Yating; Wu, Siqi; Li, Congcong; Dong, Yucheng
• Is Part Of: Engineering applications of artificial intelligence. Volume 117:Part A(2023)
• Publication Date: 2023-01
• Subjects: Multiple attribute decision making -- 2-rank -- Attribute weights -- Strategic manipulation; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.105525
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: In some real multiple attribute decision making (MADM) problems, sometimes, it is time-consuming and unnecessary to obtain a complete ranking of alternatives, thus, a decision maker would classify the alternatives into two ordered categories, forming a 2-rank MADM problem. Occasionally, a decision maker can manipulate the desired 2-rank results by strategically setting attribute weights. This process is called 2-rank strategic weight manipulation (2RSWM). First, this study defines the 2-rank range of alternatives. Subsequently, several mixed 0–1 linear programming models (MLPMs) are constructed to obtain the 2-rank range and the strategic attribute weight vector of the desired 2-rank result of the alternative(s) of the decision maker. Furthermore, we provide conditions for the existence of the strategic attribute weight vector based on the 2-rank range of the alternatives and the proposed MLPMs. Finally, two illustrative examples and two simulation experiments are conducted to validate the effectiveness of our proposed models. Due to the ordered weighted averaging (OWA) operator having smaller average width of the 2-rank range, and a larger minimum distance between the impersonal and strategic attribute weight vectors, we argue that the OWA operator has a better performance than the weighted averaging (WA) operator in defending against 2RSWM.