A Probabilistic and interactive approach to multiple criteria sorting

Download
2015
Mutlu, Sinem
In this thesis, we develop a method in order to assign alternatives that are evaluated by multiple criteria into preference ordered classes probabilistically. Our motivation is that; when there are large sets of alternatives, placement could be realized in a fast and effective way based on a reasonable misclassification ratio. We assume that the underlying utility function of Decision Maker (DM) is additive. We first ask DM to place reference alternatives into the classes. We develop an interactive probabilistic sorting approach that calculates the probability of each alternative being in each class. If all the alternatives can be placed into a class at the same time by evaluating probabilities, the procedure ends, if not DM is asked to place an unassigned alternative into a class and the procedure is repeated by utilizing this new information. The procedure ends when all the alternatives are placed. We test the performance of the algorithms on four different problems. The performance of algorithm is evaluated by number of misclassified alternatives, expected number of misclassified alternatives, and number of alternatives that are asked to the DM for placement.
Citation Formats
S. Mutlu, “A Probabilistic and interactive approach to multiple criteria sorting,” M.S. - Master of Science, Middle East Technical University, 2015.