Adjusting inconsistency through learning in group decision-making, and its application to China's MBA recruiting interview

In group decision-making, because of limitations on individual knowledge and information bases, or because of the existing decision rule, an individual decision maker may not be capable of evaluating selected alternatives. Such circumstances can lead to inconsistencies across group decision matrices. These inconsistencies are difficult to remedy under existing approaches. Based on Rough Set Theory, we thus propose a new approach that integrates two types of learning techniques. It first applies a machine-learning procedure that extracts possible alternatives from other decision makers that are currently not included in a given decision maker's alternative set. It then applies a group knowledge-learning model to determine corresponding attribute values of those newly learned alternatives in meeting a group's consistency requirement. Efficacy of the approach is illustrated by its application to China's MBA recruiting interview.