Premium
A stochastic multicriteria acceptability analysis–evidential reasoning method for uncertain multiattribute decision‐making problems
Author(s) -
Zhang Xiaoqi,
Gong Bengang,
Yang Feng,
Ang Sheng
Publication year - 2019
Publication title -
expert systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.365
H-Index - 38
eISSN - 1468-0394
pISSN - 0266-4720
DOI - 10.1111/exsy.12426
Subject(s) - computer science , sorting , ranking (information retrieval) , evidential reasoning approach , context (archaeology) , function (biology) , mathematical optimization , decision matrix , artificial intelligence , machine learning , operations research , algorithm , mathematics , decision support system , business decision mapping , paleontology , evolutionary biology , biology
Evidential reasoning (ER) is an effective approach for assessing alternatives with uncertain attribute values in the context of decision making. For the ER approach to be able to handle variations in the weights of uncertain attributes in an appropriate manner, this paper proposes a method to solve problems of uncertain multiattribute decision making that involve both uncertain attribute values and uncertain attribute weights, which this method does by combining the ER approach and stochastic multicriteria acceptability analysis‐2 (SMAA‐2). First, the uncertainty in attribute values is described by using a belief decision matrix as in the ER approach. The analytical ER algorithm is then used to create the utility function in the SMAA‐2 model, and that function is used to calculate the probability of different sorting positions of the decision units under weight‐related restrictions. Finally, the results of ranking are obtained by combining the sorting weights. An example is provided to verify the effectiveness of the proposed method.