Aggregation of Stochastic Rankings in Group Decision Making
[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 2 ] Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee | [ SzD ] doctoral school student
2022
chapter in monograph
english
- multiple criteria ranking
- rank aggregation
- stochastic acceptability index
- robustness analysis
- binary linear programming
- PROMETHEE
EN We propose a novel method for group decision making. It is applicable in the context of multiple criteria ranking problems, where alternatives need to be ordered from the best to the worst by multiple Decision Makers (DMs). In the first stage, incomplete preference information of each DM is analyzed within the framework of stochastic analysis. Specifically, the Monte Carlo simulation is applied for exploiting the space of preference model parameters compatible with each DM’s preferences. In this way, we estimate the values of stochastic acceptability indices that quantify the support given to the preference, indifference, and incomparability relations for each pair of alternatives. In the second stage, such stochastic rankings are aggregated into a group compromise recommendation that minimizes either an average or a maximal distance from each DM’s input. Apart from accounting for the utilitarian and egalitarian perspectives, the dedicated mathematical programming models deal with the processing and constructing of complete or partial rankings. The proposed method is coupled with the robust variants of PROMETHEE I and II methods, however, it can be combined with any method from the broad family of Stochastic Multicriteria Acceptability Analysis (SMAA) techniques. Its applicability for supporting real-world group decision making is demonstrated in an illustrative case study concerning the ranking of project proposals by a research funding agency.
14.10.2021
83 - 101
20